diff --git a/events.out.tfevents.1669291936.nid005423.114100.0 b/events.out.tfevents.1669291936.nid005423.114100.0 deleted file mode 100644 index 91e4fecf21ad423197b7e371126ab1ae8cf62974..0000000000000000000000000000000000000000 --- a/events.out.tfevents.1669291936.nid005423.114100.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:48f8d0122ae2ffe4fb45a5617c7bf03440791deeaa3f81b396fb67cd5464e18e -size 40966780 diff --git a/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6bd2c95353d17ed299df8d24511889166fa14b05 --- /dev/null +++ b/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 sha256:2614c041c1d640c6354ba4683da9f5907e950c418053d6546254613e216cac4d +size 3883031 diff --git a/global_step37905/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a88c2896336f855a52fab66ac3c36ca642bd9bd7 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75bbc0fba43ff43d9fafbfb0f78db5a436ecf37fd2c8903316bb762168e09402 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5fbc0dac2c187fe7e5feacf4fd67b7c664f7613 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ca4ebfd9febd009d7e52929cca6bf24f9bc2c08916420a6d4aed8a7b60baea4 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f09d54d6c0c1e40f1a61fad8d9206d69f19e918 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3a19ce76f30cdf6d2351312a050f7e3748f986817e0f2dcb28f9c877fb1bde +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e57ec044861c8c762eb189661ba8d739059fbb93 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3145460e2b17ba99309e27fdd0fc9f1e801d98053fe0dc97609fa18747ad33a5 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41bc97199e6450b40c5a7815e2cb95e480200019 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cbc22f14f4108bcc3b522bc2a4a48c7942edae14696a05aa2c2207edc880ea +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf779cd06e480f363e6a9b2c065f97be615fadf1 --- /dev/null +++ b/global_step37905/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:d44a880cc48bba6844cfdd7f935a4bb0d026f91aca855515825f5eb30416fce5 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a169d0a3cf9ca23b07f9401ce5c4888f64c59ac --- /dev/null +++ b/global_step37905/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:e8679719396eb98f0ae7727cab2968c0367f45dad8d2266aa7cd5d4f15074063 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2916b43a318f5f36058909c964c676f83d34a22b --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0aae6cfb96df215e4f250ced2068ca9f74dbf9738e1b4e9189251efb40b03a +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..78ae89c240cfe27fc8b3e1c4ec10d12f7a7ba5bf --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42e66eef33567f507b568ff1e0e891833f352d58df00dc39f1163faba3f66deb +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..32f1e7546188be1a18a414ec09f9d114246da3b6 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa9811207e31413e64ef9f163253171b60982e586e98e5f5d331847e44bf45c +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..654506d7e04e599e9c260f5f6365bd36608f74b0 --- /dev/null +++ b/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 sha256:73b82143c85faafc293bcc67f5977d8ab4b5bc2f56c69f41aa079d5a18aae0f3 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..90f717fe2c461d167da35c048ca11790773cf0b0 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c874a7c96987e4f3f77833ff67207e9f778a47fddfe04bcb18f1bb933d9c51c +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b9a52fb8b0d47c794d89bdcb8279fa15734fa9b --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aae21530af2ddf3ea14ecee52d98091e9bb11254df7d7ea48c744b4f550c219 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..733481e45f6195cb4d262f68dd0a31fd9f873ea7 --- /dev/null +++ b/global_step37905/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:e90241220fdc6480dbcdf5a18a5e0105fbd046c3b1e70671a35ed9bee037111a +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d21222358f9d4e37c2046a8173eb77862e4429c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6795b028a2b5c630e7405ca51a3caa27ca9324abf9ff9ff9258864e6d0085843 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9226b5499dc9dcf6a3defa7d9eb9b2366cadbf75 --- /dev/null +++ b/global_step37905/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:ef301ebd901630b0db5bf172c931b4f4bcdf74be6b874e7de27e342caaedbc8c +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b0bf86066338a010c64dac267578b72b921deea --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d4ae0d2aabaa6c867c235054ff25aac2d65e6965779e5b096ebf16224a1f80a +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..18ebb02d640cf5f53098dc3c25b9a6ee08021f16 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956de56bf62b7fe56105bce38e6a32213fb23cbe69be38cb8fa8962e9ed5001b +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3829eb4f020c76126374cb70766db9a05e76ede1 --- /dev/null +++ b/global_step37905/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:dd93ed0e6d973855ecd9b6158086cd06f6ecdfac62f088438ff4ce0a046b2ccc +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b8e7b397920451b60ef441bf36324903110e707 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738158a1a1962351703162d02d5eadd01750062635780d4fd8eec10943a8bf6b +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c43bba00b004cfc5d5e0ce074eded69bcba31aba --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a4ceb489b68f2b63f6a5bf58ac663864c8f0d5f30a9a866c311b3a2cff2bbd +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa96b50cd2fb8e9d4c756bf99ac2ba9cdfbb200d --- /dev/null +++ b/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 sha256:9747a31e138952fff91dd33bdc673d3717943abeceeb582e27bdf319c9c5e266 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c32a5f56441932b5970ff756458ca3b0cc068896 --- /dev/null +++ b/global_step37905/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:fb99593bb5747e33e96e5f92c2d6db36d343c87939d023e6c10be77b99452545 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae56b676f786d9dc66882fc24f2a0e0df360edb3 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691558342072d60a1573ba14b5966943161cd36ba0dd2059b3b206b26315e7d6 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ef7cd12a6360f14195fe1d6761619482e30d90b --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7505f0f07bd9e68fd6978f6fe60e846a57de94f136419c7ca8d8492674f1e991 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..24336d1b1347f6b95aa4b33fdc266cf6ea53a4ab --- /dev/null +++ b/global_step37905/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:e65e616d1735f90fcc485cc8712a3bf29ed3a6fd133de9eabf13b95a3a017088 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b3cda3955b131e5872c50f4742cc81c858ce000 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55367612b4f0c8dc94b47209a6085bcd2a5a36454385775733d450e86a962324 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff287a837756fc2c1ab33e83efc7bb110763f4f7 --- /dev/null +++ b/global_step37905/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:ed1bfbac0de96b73c2a28b4ad25f6cd1991d1ffa50e8af243b2a93c968ed690c +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b203265fbd9e20a2630e8d0832cd469c696427a --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb1ed70d1a76a83b3d488f709ee1056a3688efae0f36c7b4780a79d0d082679 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f5e5be81423b49122e73465a6355c026ec80bb1 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2702dbb3b4c370f01c002e61c96c89dd72975faf2ba6b3b5c43366462e4ab7f3 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2747c442ac05925be705b4857dfd65350a44d79b --- /dev/null +++ b/global_step37905/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:f7c16e59eb28a0d915efa48c4fa009691cde2141b7bc8a8d2fe7dc1dd18c8897 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e5d654cd78fb74aa28d3c78a937f7dbe24046226 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80895f9ccc5546ecf370f8fcf908b46209798f65f317097fa0b0e1b3a8998528 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a0289547ee7efb0b73015239230657794189deb --- /dev/null +++ b/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 sha256:4dadfddf8b987b409f2c9807bb4e84b94a6881d95e11d531e1424530fa21c724 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4cbde34462d160ec8b5560d07e8cf15179d6a46 --- /dev/null +++ b/global_step37905/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:b71aa01a958c50e9b802b4eb5d311839e91e19ad3ce05da28d67ea3dcf1bc6c4 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..751323b81d30a5b1fcd4eaf746735adab073fa49 --- /dev/null +++ b/global_step37905/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:f1898380b4dbbd045520f112d0c601faf24d0f9219973e8908b4c4531b5ec604 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d554ec9be4b1b39333a28daf184755503ddd310 --- /dev/null +++ b/global_step37905/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:cd3d0a12774c5fa93701f37281664bf63a38716f7a803c1dfdfa6602960e1244 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d47532e6ebcda9c1b32fbbe74c63659dad811638 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cbb76bb31abe9d64d93ef762d0df84cfaaca8c08f9601a89901f3bc23a597d +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce2bc6a8598999dd42fe20ffdc66aae8f76f2ba7 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2643feb868ee50d5aee05cfd08a9d7ec53bae2ed5804b2eb11309b95d720bda6 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6c821db24b03477fc69c3837efe9a0b67032f8d --- /dev/null +++ b/global_step37905/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:bf1289d35a0e0723d4f2bf470f2d734540aa3133cfb7da009afa628cffbf6774 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..08733a1e75330e568d1386f2eb6dc5a06035913c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4c6a352ce5b777898817c64e3949db678d0b45a6ded9ce84849cf1416925ce +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad1534a2f32b9b6b7d326c29f16269f259d34392 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4ff31a3e235e78690d638998eae258ace2b721984fc1380c146f86354019f6 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9305332932bddd446ac0ae4e6b5068f779a0951c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d11a607675d500a3759a7eff768fe009909e3871a8b138b62f8818869f23cf +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..45180ff14d757f4fa96ba292908b5ae41494997b --- /dev/null +++ b/global_step37905/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:d9501e366072b25303188dd4ac2dad38538a6905c508af1ab3804b8ee83ce1bf +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fa52c545db6bcee22c7e6c71551605e5ba9b001 --- /dev/null +++ b/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 sha256:5af206c1ca51f6c95fa1c3fa1a0a457a89edeeadae404b1820c90dc0f7ddd6f7 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e74c9ff4d152b8639d19bf0e8f5f1b1e6c0a70fb --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20bb06a5d83a0929fd5141240fe0d1bb2b4fad699ae31c5dcc12752b6583b8a4 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..397c75284fbc0eabb0ff3f1313696099e4a9d787 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f4c04d49a00e5e543b089e0bac521b5a93cb1e865c0337d26a4d780d20ab36c +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b3bb957acfaacfef488998c273e2c61f039bc38 --- /dev/null +++ b/global_step37905/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:f6537eaf66cb0b598088e7ee0333aa9529abb4c681aecca12fe87745355411e5 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7dd465a2c9682ec9de29ec7f46a679ea84ebd1d4 --- /dev/null +++ b/global_step37905/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:bf0ef283e8507fce6579b716ef417841cb10284e91b0b515efeab0813274c608 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8476d1175044bb121debcb53519a14c67dee75a --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677c62dcfd17a99cebc7574640cece009319040cff2483715b86b6f7aa86246b +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e28bfbe7768b4cb1b4f97e0d5028a2712858f8f --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:234cec8e2a7636acd8cbd7dda8b48c81280675592df3b336d292bb7d7be97116 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f0f1e7051f350db9edd16f1cdd1c342254b83d0 --- /dev/null +++ b/global_step37905/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:d801103b74288e9c03f4599f3cacfe2a1441d92c371df440dee4761a2b6e90c5 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3baa7be91e4e2cde0151b5df1eaa0f91d7f8b8d8 --- /dev/null +++ b/global_step37905/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:edd1f0daf5e2c0761a9f65621e99ead3b2566126ffccb7ebbca95e045ebf2149 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1b08ce55f781cc7c516eebc0f15b0e4630e0bef --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d9ddd222e784330b328f94e674b043e98a692c907936f8bc02b903510f7ad2 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e0db348113189b5694be6cdb7998ccbae3d9262 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a534dcab28045df7bde5cbb161fc38e338943953a8353305b33ba407d7e4b0b +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ea89da5789481afb68faeccd0a961222c9711354 --- /dev/null +++ b/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:b517c983e4aff1ff928063d4fb91ed267871a25f0113a65e0723044f36bb1a56 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2884cc8a463ec330fcaa3f25cfcc920c55791fbe --- /dev/null +++ b/global_step37905/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:e578fec7d7c07133e2ee334cd6589058984ecd9e556cdb2234ba84396cb479b0 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b20edc2427a1610a79793b81cf9c13a3781d95a --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6358eacc209a5b2338072a8c14b0ede2389d10f9491b263c1fb795d3f59a9ca9 +size 3883181 diff --git a/global_step37905/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..63f3fd70836649a16b8a453ef017d97655bad271 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f1ac4f6d169947aa2831d7916212fae7045725f7b66d68cb820b8569ddf9f46 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..75cb074fe7b9fcb63dffecfcaa453db3578f3ae8 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35da5262e9ec4053b709cb8ca4ea25972f84e92669fb04f3e96e635338450294 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0d742ac9d88a28900015ce8800b20248c8f517b --- /dev/null +++ b/global_step37905/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:bf509d4f675279bf578cf70353c6d379031981209ba75c9ec4e5c1ceb7efffd4 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7de88bc347b5ce0b48c8724376b0cfa06f025df --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8300b6446f12948421f904fb3c1b62afe997ae85daca444d6749913895df3b0e +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..43c609b3b6998e515b65459a0ef5f4724e16ac7e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e6ab1ba8a479c01b2a02dc83701091b3c72f7e54932e20e18b14ca8e0a5acd4 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f93ff57bd2ce0ef54942965ba623d14060fd377e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ffe9b0f2354f654260270844ad6f3dfc469875a1f7cf37bc969536aedf62755 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9a1bf0e0b982dbcf0fad89a7795cdcf9770eb7c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd091ba8fd1551af0baf37c5333ccff4a1cb996f631d7961828680963441312 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0bb52e57aad5479c8cc3b38d7d232c0bf660e23 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39feb13ddf09d3f90727b74150c7613397dc0db2f1b244e4ea859865ad997e7b +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fd68f9b9511d82a1733ce6746a3076aad57db69 --- /dev/null +++ b/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:e81a81e990b42f5e9dacb5f22a944a57996ba6cd16096ccc7ff8be1f2629fa5a +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..291e22b8f14d7ee047cab38d2bb1fa36e0c4db33 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c897cefb81c785562854ec2a82f58b42d4ecde317a8b6cbfba9a4ec86c9e685 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6494634897cd26180547b68b7d49417ae97dbdc9 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6bd74c2e4590b35b247485350f545b7dd8c6aae1f63f8020fad1d711c19b79 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad26a4972fcbf1664cc960ef97bf05cdb7622033 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585e4f03b8823365bfc756e66f32e736d7a9d5764dfeed8966c2920e7cfdd5d8 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fac44955044b68be6af051a0a258221d8489cd0f --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be33de5f67584a89b708fe3b0b6130d3e212453640b65d7a4af7fe7b3d129f1 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3359bdd526b3f4b537087f78a2a72a99ee99d6f8 --- /dev/null +++ b/global_step37905/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:f656e5f09c24881323a11865b2e06f10c3aee0cd0c19ef84e0d2eac2914e9d74 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8594b39c08f5964cdc746855d1b97b135c474042 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4384a20fce76c261f7aea3b1e9cc5a72913ebf7b86a933b7e3461a0844d3c36b +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f693254504b671db9f94f397c49fb477f3af09c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8b21d75b7062976da00e41f5937729a0952e19bb18d848989b229c484ca457 +size 3883181 diff --git a/global_step37905/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35bd85846ffdf54fc0e2d6c9a3ac00e2916b84b0 --- /dev/null +++ b/global_step37905/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:a9f4a45bf99c6314a63fdc3edb04322b8476f1657480611e8529b4b358740242 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c881818318d44e6964c61dc4ba1986b06ea4823f --- /dev/null +++ b/global_step37905/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:cd86bcd7949bf9f96b7465d60e956ebf88df3efacaf8fbea08e9e3701047d96d +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34df28efd304eefdf3f8d965cc5220158714986d --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:213d42ea8486a937ed31c15cec43a4049b41f22842d24baaa274fb73e68375f2 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4dffeed7c84e85ada532068230a11441bddd0ec --- /dev/null +++ b/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 sha256:145024c32a8435021052d0e07a6015670590179dbcddb9e85dacc30efd2bf659 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a736bf732cf10607704278e45e70526b8d331b71 --- /dev/null +++ b/global_step37905/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:cbd0f40800ac24761e5bd60cc23c88585dd1fe6b7c21eb54ae846e485143361f +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41ad873be0ca29dbea867e574bb8cf3b86613fd7 --- /dev/null +++ b/global_step37905/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:c9191f6a1a3d0d5b27b95ff667ab4097fc2012649a3a01f08832838fbc3524de +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d2638a7ba76e02464c4a829de080453021879cd --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14cf11243cc79f794913bedefd10b3dc12777632e917d29fb5fbe37993b249fd +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..042f1fe6e2be1e84bc3c5538194f766bcaa53765 --- /dev/null +++ b/global_step37905/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:e460b0bb21091dc23946d8a5939e4e9713b250d5de682cf166e63e7fafdc0eb7 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc03fe1778c31d14eae8659e240d26a88e12c270 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a065d0b943469605523fabeefdc157148553e97c44ed01d054d2d2595ffef6e +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a50d49d48a33bda4212798b3495d07650f8e8cc8 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7540cfe2ddbba79c43d877180389f47adfef622c615bad9582119095d64be426 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f00d8ee4af808fe42acae6f6be2ed2f546eea3d --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9af1194bd32b1686822e56279534af933b688cc659352467004e58cdc61a40 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..25e4d919833aae5068ac7533d8b304bb190ae133 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e93c547033156039a0309b82d423dbd1524e0b68a860256207594f9b8e06ec3 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0917a0b1324b410a18903f698d780c5ddc968cd4 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:612cab548cb8fc97010d8dd53ece6dd892701818a9fca4c108a3a5a1674d10c5 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35a62fed028d1fc82f72e520e6b794ae41ccdefb --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7262bdec35ed420525cdc58c1e8d884f495d2f32725a8ad61c43c7276b560f +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0df03635e1e45bdf696d3cf07c5b14852c59579e --- /dev/null +++ b/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 sha256:32f2470f9701468eb5d505d69536473486b53946e03f8ddcbd63e4e1af332dba +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c22d17357dd8520d8c7002a90709254792caff5e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ae151f8d0847daeeb1cc53d9d88b63bdafd2f9cb6b7af1301151f1f6eab031 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d306e63043cee1943c69a37371fca8b2c49dd4df --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d95a1e8a657a039b0a1f38c7ef0721c9176a73cc2577f78df7c467e441acb5 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..33d208cc1fa6b02b46b746bfd8baddfcd13c136e --- /dev/null +++ b/global_step37905/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:c505fa1492aef8d0f4f5d7334e6cede6aa5a071fcee24f240da692c6dba8b249 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd6a8f86f18f6bf07cf6e721ab3382d83cafb49c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e192a6e212b03b3bf840fafc810993cc7720c0ab5b8103378370ac8bb31244f +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34e96f1f101a28ba244de576acc42163db599d68 --- /dev/null +++ b/global_step37905/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:d092bb18b3d6eafb16fb7f86c36e12772227a1afd7233b2582dac1aa4f0ee884 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b23359409cedca43eaaf9f99e2789757d504c4a4 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc07eb413983195eef7275372b65777e2b47b589e5ff473d4b24d36f136e517 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fd1e6a12f14ecf59981bac2a672e8b85c26a7289 --- /dev/null +++ b/global_step37905/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:a7205334f6d4c5f639f71d2ac6de83d024fb865343aa2bedc7d03cc7f53e4970 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ea1ca583792db92f0cde0d01d492d414f843f98 --- /dev/null +++ b/global_step37905/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:e3ac2ba9ebddae3522394d08a80f93882b168edd5148ca5ea0612534d29aac45 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..64c7e64d1afcf844060c99a37457521f521160a5 --- /dev/null +++ b/global_step37905/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:d547a89e58d4c64f93811301473fe27047881963858b23b728027bc36db7c674 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..861c83f6935503a6621a49a833835651a712bb32 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d90edf76cdd1abf24d8b2ced72661737f599ea3b5b003d65035e453d3dab32 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..151ab55c34aa8fe4aeeace3eb95c94bc5472153a --- /dev/null +++ b/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 sha256:93a07a89f8a4a2f168545a3a7387baa2537361abd2aad874758dc5129c72810e +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f02351c03f12f8997b0b3d28c92c9a661f83d6b --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa444f0dec3cafa54066b1668be762b67b714028c8647f1cf6c670eb49730b5 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e502bcd43bfceacfa07c8ba26c04505be395e330 --- /dev/null +++ b/global_step37905/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:a6de76cebc0a6da0d05dc84b07eee44e36083f0f3d993b683112f115bca80af8 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a7457c81db9ac2cf96bf4df58b264316f44096e --- /dev/null +++ b/global_step37905/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:d855f970c621785352e8c68d5a8acdba24a06c90af62357de740f6e3be713042 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..734a87d44af1e8bb4f5a6a10af238ada942d3b26 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffb1d6c781176477a59042dfd6fb40ee821c36c9571ce6173fc2731a7870dd9 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..22bd406abc869cf5fe651c8978533fa688800b37 --- /dev/null +++ b/global_step37905/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:a6d550d8308a10f2f57e442189710ca0b873cfec39c2886b7dad624505d7b4ba +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf8d3f6fffe8ef6ce27fd48a9fad389ce23a5bd8 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56baab9dbfa3f037d5e454dea77709848b24ffbf795b65fa8e5ab043f362bbe0 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..96cf61077b38dd1af406dac59dbd2ee7e23a81e9 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:294f945136856d0ca1a1172c87db828da7690f83412355137419fd16821f2fc6 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..db25ad05d62e4b0011766721c50c2c7d1baebc98 --- /dev/null +++ b/global_step37905/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:b1cba62bcedad9c626c8d66da1fa01c7d3551acc43353ac88207e70ecca8a697 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4339345835ce78530a0cd5f86ecf41e376f856b6 --- /dev/null +++ b/global_step37905/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:be1fff87e39c2bd799db3fd001c3936d4c5ada34c28673f850cf2c271f735a73 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8560de69f25dc4df401ff6070b417f6309796494 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc44cb3726172e1391447c462d9330f25eefb4cb599bbe5e4620daf2e8fd79a +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e12b10d9d8edfcb80e62683041f4143a44a031a1 --- /dev/null +++ b/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 sha256:5517f9772788cfb5e7f23eb199958ccc535f4bc82bf7074f04aab2057a60d5d9 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f289d5bb919cd032a925fb8911dfc11ccd1df841 --- /dev/null +++ b/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 sha256:77c5f96fa456e9903f5b52262bc4853c6d9f3c247a17d68493eef6790546b159 +size 3883095 diff --git a/global_step37905/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e37da6bb3669e1a490ad35c7e4e2db4400f055c4 --- /dev/null +++ b/global_step37905/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:a3e7d50f4f3cddb310dfef1de6a184bd14613e54fbc1e447549db6a2bf1f4152 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa8538be918f57630b41123b969a7ca5cd70e546 --- /dev/null +++ b/global_step37905/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:f2edfaa74f602ef422ad8f9aec9ba183fd711f1a19ff9acef1697fdbdd805103 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..846dd41082273c947acd8506628d5ad67fed5b5a --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48cc8376c3e3bbf15a885e8ac467be1a3d30a22b46d9111199d121a5e076cf21 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a2e4f42107dec289d5e0f3800ebcc749763b5f62 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c5408fcc59d740fa522220be511166171ad7286178e6e274b5c0a64a5cfe13 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..370b3a0bedccd8f0ae5765900351a47c4d583ddb --- /dev/null +++ b/global_step37905/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:c9bc9f97fbba9b07e6d543862ba166d14dbfc77035c60e8e4d4faa2a4e359cfd +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b12fe6f5cb2f09b7e469d09b1ce0b2d5da6d15fd --- /dev/null +++ b/global_step37905/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:ad8b55635e229d50ff3c32045075867a892746e782657ece85ee77ad47ea3f27 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..92342da7c57167677fa65af2fb927f4f7b575d0b --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c9a2ce2cef5f2e009b55242bf21042c22e72bda504c2b24bb1c4fe285a8e84 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa25cbd44b2bd08bd9de907db4b544ec93f6c272 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6103af8e3b6cf1a0ebf3044db84d5be46b97998765156b1c8dbebf931f80a0 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0a1b1db41845a6ac24d16a8201a0c86d525b2f6 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79dc78aac6f0b093aab0e45195e97d55a648590e408c010cbd2ad2c2838e1a2e +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f19ae3a8d45ad9db186fe12675078848a7b3014d --- /dev/null +++ b/global_step37905/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:b52d78ba41610e294793bea4982191615e88f7105f0f2a740566037b406ba2b4 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c57661681a856ac3ce93f148dad56bee5d971c1f --- /dev/null +++ b/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:f295acca807c1ff026e191e0d0bc850f8377ff6b5d139b735112909cc52f15af +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0755a39fdd82a1aed10151055b44b22d666d4fbe --- /dev/null +++ b/global_step37905/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:a816cf7bbcbbe3c8482b71e98c485b5f52866bbd5d903651cb694e1b64419241 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e13e8e63f220d7ee7cd8798a17baf3da6e99e458 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d132cc7a9d3efad46e276db5a44637098037a88668f470e1edecb9735e8ad0 +size 3883181 diff --git a/global_step37905/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..80158c517fbf5ff8a7cba06f8a3f9ac45296b228 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175fa8f9b38e1be2b00d9ca408824ffd7d02e174bc31ef42c72420214d59d400 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..746ad136a9328300889fd58a7d3a885bb03179e8 --- /dev/null +++ b/global_step37905/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:b81d675ae882477be2f35a1f4da719ac00a492293b1abd4a14c82eab2f85a465 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e11e298bbb2c7a09df8ffb31d9939c8bca655cfa --- /dev/null +++ b/global_step37905/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:e314387765ad854cf8644364303cd30deeb823ffff3055942709c6898babdce6 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7263eefbc7894fb2b90fa27d4cfec65e9c70c56e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e6bbfbb51daf2fe8316d45d67686322dfd74e3d43b32278dad99baee6fb5196 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..05c58ee37096ae357bda494eba846002eb9a9a48 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd9e3ee80bbf5c71e9331f7d81cbfa7a68b305e390fe22ce04f99c1aeaf8adf +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4cd248af0de924d785ed6e6bc0c1a213c49d2380 --- /dev/null +++ b/global_step37905/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:da85912a86f5448730b713d2ec3c6e2b93f9aab7272d86b593306f9f87598756 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c73865fc44135fc305e6cd4f81e6b45f467c7e8c --- /dev/null +++ b/global_step37905/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:b989d07945e5e0c1c3af7eb0608506abc6ae2b7814381bd3196f44a62486a2c9 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a01067f11679126f6757e78cb150c52e1dde6b9 --- /dev/null +++ b/global_step37905/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:eb07aa3e314a104ce885972eaea14d930e41eb916dbba55a560d2e4f1215e319 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..05c1b82284c72c4d87d679d938b47d49d2409938 --- /dev/null +++ b/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:c7926f3467c15b07aa3fb6ef5cda0df9a6972b530c867819b069148f0d48c601 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..13b3ef6f510782d71fb26772ecda24ce0211c086 --- /dev/null +++ b/global_step37905/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:a4fe56187e85534c8d40ac98358254a5d6d24e9f4e74f5eed48c6c1901665cc1 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..beb1f12154c18b73be5ec03be0ce0b7cbd4ba09e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d297cfed0d8cb28c13eba3be219ec534ce5fc4b41336f90e4be4b424d1bb99b +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf7f479bd84bb9c56350014f0244ae71a866f004 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab1d7311d536345b37666c7983a53294892827606b3c086535fbe00658e1141 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7593d9160bdbff82f154fff6f3e7c4cbcae59754 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32638e81cf78e2c4d8467068055573fb47c90d6d4e716e245b355a8fb71c361b +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c904ca039cd21ff37f98056cae3ccdede04035c8 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dbcfc878bbfc4a7023606f5a697db534bd49dec3a192dcf84cdb538fd9796a8 +size 3883181 diff --git a/global_step37905/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5c2f560d8cf3f91476b6c039f0744bf0c2fa9d1 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703853198903e10fffb6e34087ab1d72891505a7c82ab3b804c97f8e68746f9d +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..618c8f2e56d7b8f7c288d6af7cd11b1756d8fce9 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88abecc72e4ac2a59c06cc03d9552b2e1dd4ee50bb550ba78d5ec83bf35b989d +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..27c5b026f1aad1439eb88684ea7a7a69cd8e1b04 --- /dev/null +++ b/global_step37905/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:fe681140aab77a28d58203a767942a2a6545c5cbf2c795ebe0010422b8bcf4e2 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8790fef3c78cb282e28269980cbc64d4477d0b05 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ea09dcfd5429910380bc52b9a483cebf8c614aa7ab402df2fd639ae6ca84d6b +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9f4c94327e85b17e4356521cd2abe4460efd573 --- /dev/null +++ b/global_step37905/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:dd0ad78553c4b40f6628541218cb571db394b8e07a20162573c66cb44b0e320c +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85546d0cc72be8509898323a69f014ea5a9fb701 --- /dev/null +++ b/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 sha256:7be2c9d48a87e134d14938798339311d3106eb865bd473b5062a2b7cb073912e +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf23ebaf9752d054340ee285d9d4a29d985d2559 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c21624e6d77a1291e197637fa6d951565b8589b09af4ac87585d66190635c1 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..32eea74df24f5df2c170c0b7d56889f2cccb8fe8 --- /dev/null +++ b/global_step37905/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:e52cd0d9c07f830298254379738b07382962a76a348781b6f531e294c753a2ce +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ff43cf0a9c40f33db300847043a93eaabdd7fb8 --- /dev/null +++ b/global_step37905/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:be0d6f1a98e8015e2d37fcaacea222cbf5c716ef720d9b5145e178a678d24f19 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..35c09ad0d52f750d7e57fc13f472463e0b738adc --- /dev/null +++ b/global_step37905/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:cf74bc331906145f00f5e153a199c2eb79bbd5d7b8f6186190a63b1a74bbcfde +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..406e28d318150fab35d1dc8c7470a8f0241437a3 --- /dev/null +++ b/global_step37905/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:ba9160628c201fbaf81565925e6f26a5140b416dc49a8ff32eadf351a4ee8f79 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..81032eaa97d646d5227d68db1251c361b85fd84d --- /dev/null +++ b/global_step37905/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:db4f08139e09332cab775542821593266417ccfd162914a55ddcb2ccc3949fcf +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..16aedfa45c44d632255c7c1257af97497aca8884 --- /dev/null +++ b/global_step37905/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:d51e68d537e8e4cd902cd080d52926bb8d1878d43409d63e0ad07d6f4001696d +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e1881d689a0aa6ba7e1d3f92a73159527fcd35e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78b2f0801758dc3d12c94a9e887f806747fcdb0e4388c94492f62b1061bb6a83 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ac6e744a8cb55ee58064f32a35327a14525b946 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b5926fc7ac8be2c3b13745855b76ec324a5f874d08cbbafe56e70dac20e27c2 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2baa66ea9bef6a353e70eb86461ea0b10cbeee97 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57794c34de63780df61963ce9b0eef97001433054d10be091e35021c58d26061 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d23e2240d8ca05a381e562e6e3219bb3e5a8abb --- /dev/null +++ b/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 sha256:550d4de26275a9794441092f5ec41a6a078b449d57d110de8cae5d5c2b10f260 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e743f5d76401efe8f28ae0a7a3370e805e437b0 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c23d6fd15e68141880e2033fed57b6d009efe2af3c7f35af07b41b1608c4c7a +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1089f1f9997618e8ff37e33bb475a57137e6ccc4 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b71b0d89f92d151e3cdf01f38b899008ce5e489d0d53d8d363b3e88d64c418 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da7dd963139b57ba9af81876d596a9bc16415738 --- /dev/null +++ b/global_step37905/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:a01450710c983e57de8d45861386e6447deb8645c182eb3029c68ef14833772a +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34e172845f53a1870b32bd523cb185b9a9d0bfa1 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86478c0361fb0c37072637384a8653f908da1daad8910d65663ac4ed1d240e6e +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3829b17c11eb8e7b73dee1f51c7d3bd2ee57700c --- /dev/null +++ b/global_step37905/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:f4933c9e1e7dd39bb325f0057562b6010530cc94f1bc21bf8922c6f4fbf6e416 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0f1d34f8677db0a1b1146943cb207832b92953b --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e30bd189aff0df2019024d93c9a32434dc13a6f17ac6edeb22c20ef87becc6 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..29e414a906fcea0acd5e5e24d0590145bf670827 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b9f1988f115be934f56c410a6d0dbcaf3f5da0ef37da432be2bcd15832187d +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6db7a06e2e0577becee2916e4133fd834a10cc3d --- /dev/null +++ b/global_step37905/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:df43c0ebec0e476adb29c44af0c674640cd103284dca5b5f3c7eb7293957c664 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..468d657f3a8dd5717e787cd46ba9a66cb7eed2dd --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b800703fb46285fad6cc4e4fd4859f8bee93851c38cb7eebcfeecfd1e10345 +size 3883117 diff --git a/global_step37905/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c9d69ed3378f8ec5694b08d5b5ee937e199a2d07 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4562a1ff6e87e8cb2b7da119d1da4f4fed762fd6fabbbb3e51941bb6ea4927 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..604829722f44bc921ca726e44e1bc49e5e333147 --- /dev/null +++ b/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 sha256:40ab699d7286b0e91eeb378364d9d46984bab4e343f98d9e89c28b0053be9d26 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca4e2c660e37b692f47118fe43a624052ab737fc --- /dev/null +++ b/global_step37905/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:e9340b0b1eb17b8c4f6ebb3081381b0bf3b5517f48d02b437586ed4474538db7 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d48f5f38f89c78ff1309a76db74bdc05ce7d321 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848b4654ee4170c3cc1e27058f453bd825ed3b25256c580e86f87c158291cf3b +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..03db3874b47b8910f5c4367b435345f410328bf6 --- /dev/null +++ b/global_step37905/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:caa4a7e627b94b1b346f4f7197ebb11d0b4e5d27fee9a4d3c1d3e1d919dc6bb9 +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b41a46fd8e5167d6d50dda586a01b3d07b21eaf --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6880aa9444f500c4fceb2530c1763d8b789e8ad53f56979f086e357def902756 +size 3882989 diff --git a/global_step37905/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ade92bf2b9fab42ed205f81d4e098330174876ed --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cca6257b9f71b583bd807c353cf66f52cced3c292ab3bdeb3888260f035e53c +size 3883053 diff --git a/global_step37905/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7a4b3a5a65ff08bd32fbedbf8ec6517c9aa5e11 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27afd557bb0aba9dd74125967423f56501bcbf85ebc3f369d29d424c074781a7 +size 3882989 diff --git a/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b4bb5ee1418e3060eb3a86c869a083ccceaa84a --- /dev/null +++ b/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 sha256:9bc16d8b173151ad3223054b540080d595b4b2dfcde6ebe6ca2582d94cf76580 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b20b58a4f1dca5b4f59f709f522e1b73461019e --- /dev/null +++ b/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 sha256:9ae203301332525c68c37bd2b7bafb8f990f0222584bcfaf9902a992ca55eab1 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9cbc4abe0bc0201f2d05d35ff287cba0ec44e2b3 --- /dev/null +++ b/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:d8cb21db3aeba9367a3383e64b2c985295c346fa4acf73969699e2af2d5eee86 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..266b554b98f20b749c48b5e303977fec8dea26f1 --- /dev/null +++ b/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:dd4933d6524ea165ed4727faa09526e41eab1ee32a29553b4bc5d58e50181971 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ca49d9cf2e62fea4cf1d41fe66608287537b345 --- /dev/null +++ b/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:e70094647800ab2cf340e8b155b33cb3f04187e2bfe4691b8e72ba94a9f1ab32 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a96969657159a93b67ee7a9e3187d30afd0bb568 --- /dev/null +++ b/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:a3be2961510a6c881630e5af98564db15eabcb4415329c9b63ebe31f8e94bc63 +size 3883031 diff --git a/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a6a35a40663e3e2f88e36fa4d981734e2f53e48 --- /dev/null +++ b/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 sha256:087169d0d587475ad322329a98e469d1269a1ec347c525cd9b274d71abb1dfea +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3853b860a4b7a06c53a47019bac8b1bea8a74232 --- /dev/null +++ b/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 sha256:99d03f02ffaf637c82c9cc97c8a5e0778752c8c70b7efbf719bd6ea60cef1cde +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7deb34a7270c5a1716551911fe45e56234c346e8 --- /dev/null +++ b/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:f018b503cf66be1366b636761632a56c8457a07e25927242ff549e4bdafa70c0 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8fafe7a9e043d3fa38fb1e979153a3507bb63ba8 --- /dev/null +++ b/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 sha256:10fa77714b8ed0385d92169206c4390d7b1935791105b50c95ca34fc2e32928d +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..05aadb2dc64b4e97c5d9b47dcce56b4aef111a3d --- /dev/null +++ b/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:e2e4c3b95f60ebcd42159a8d921dfd1de4d69b969d280858d94ec0751979ed67 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..26c0bea7efb12ee7dcaafdc2d8eec37aa499de63 --- /dev/null +++ b/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 sha256:8a1e6aa24206c0d97b3d8321902753b32acbcc9bfde821eca783bc9fcaf38127 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb0fad4fdef0b414682defc9ba3889d486b6e4c2 --- /dev/null +++ b/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:b18c4f752ee199490e0996f8eea6fb0aee3f7b7a3429088247b90f5fc9dea9b7 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e6ec6a59d71344258ebfb7beba1d980d25ea060 --- /dev/null +++ b/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:eb0eb64084cd1c349de6b60cf84109ee20a2eef9d89836d8cd9d079a9fe9495f +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..46490961742788fd76a6a333790769b3dc4563ce --- /dev/null +++ b/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 sha256:10308fc9f79aac3436fe3ea6b153cfbf186eb14b1b659510930d16324040ab0b +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..844348b5317315c1967126951db44ba7c5bd47a7 --- /dev/null +++ b/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 sha256:6a9246844799941c763c07e34915e40f068760f875bd193ac17e0dd8fd96ce7e +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..09914f101b914e96bbd08189443ace10f098e828 --- /dev/null +++ b/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 sha256:1d638bbbc310b8140db2f28310c8730fca479fb54f77a9a10c773661f15dc1b4 +size 3883095 diff --git a/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ade9af451ee9bfc7721da723a35154281773f9c --- /dev/null +++ b/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 sha256:18506ab20d6024e7aa78f7ad8e7b42f83cbb4b7f6c9f0cc52fd9d959180caba7 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..681db0ef8dc8bfeae146fb50fb0abf1eca9c0118 --- /dev/null +++ b/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:b4e08a5ff6984d5e203e706a42796889480c784acd6a0f72c3644d1dc04f90bf +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c0efc10eeb1d1b64162dc30d99d2819390adfda --- /dev/null +++ b/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 sha256:9c8150e03b3ca5712b9d1ccf1d31ebaa337d9f93275c257d8552157d5395c2a3 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a15967647c24af092aa4d23cb23a5230d0c4fe2 --- /dev/null +++ b/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:b81812be654738e128d5ef2770cbfdd8a6a7857f85f303db278659a3d57cfebc +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..253391e6cc4fedc639561d28c7ce6a010c04a85a --- /dev/null +++ b/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:e76ded25a6c9eeb280ce21b617426388e1545931a5bbc71359aa2f06b368ee55 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d42fd6b63c8583c8d02b5cf0c3f2a7543a3cc007 --- /dev/null +++ b/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:b6d544176a06dc3b5d419249155d6b7d473fd33283bfe06d166bf2597a68fc86 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f906a2c144ab8d8d40f9755392356d17a88b20bc --- /dev/null +++ b/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:e789e4c3cb10676e0fd45c19f23218c18d87fc3bb207540b5357364df0e1eceb +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..854681c72b769897b02e0adb549190e41df2aec2 --- /dev/null +++ b/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 sha256:592199ada2afb3adc9aa278eeb74531a4ab9de7ebb3c454a963f99fc51e84758 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..156adae290f65b58d60a50a2735d6ad7da3b3c18 --- /dev/null +++ b/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:cb5f17732c23d6ed8f6fcec8cafd8122548ef7b25a0bbd3000c939eafcc62dc2 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac36aa561f8ea50adbf05fe709a7a4b4cf127e80 --- /dev/null +++ b/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 sha256:54dadc51a14cc8459a98fd8c1e19fcc1ca9aa423713a1595ca361cd063309508 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c986f5813841d0e7e73635b8ec8aa857fa4b170a --- /dev/null +++ b/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:f0ef172b450ba3e89e8e4434305e6dc7d408edcc8a6178b857bb58bfe45f7c80 +size 3883031 diff --git a/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..674446cf26929a1b07400513adfe4953147e9bec --- /dev/null +++ b/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 sha256:49e10913d82c83975c923d64c870acf922a4585e6f90aba83199946e62da3867 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..73a76c3b51fde23991f50234eca3d7181dcf9026 --- /dev/null +++ b/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:be81fff0f081bcf36dbd259b35f99de01f571e3d080493af0cce6ae33f724882 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..84f9f75d7b95b2de8d4308544201f4b599e55076 --- /dev/null +++ b/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 sha256:419a2524d706f69fd70a6d6a27254276e7d743e77353de8efe7357f1e5d45b96 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cf55c72ce6e43f22c2b33a0845435698c2f94d7 --- /dev/null +++ b/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 sha256:6678024892959f617ba7fbb3becfdaa01d6cb1b13198830b32803c2aaed745f2 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..246504bdd7190b09c967b5ceb248e3e045ee70fb --- /dev/null +++ b/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 sha256:218fb08a85104ce115c5dd00791a1e17c815ed0e6aa9c0f13ba6eddea77f2ef9 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..98968f840547f17693d9e26088a023bb77e1dab4 --- /dev/null +++ b/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 sha256:92e64c23f8bdaf49a5f4a42e89aa5b2041b2606a0b89b9145c0c1ad1329e4e22 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f33acd02de0b064e6c8a215f5dff065274af905c --- /dev/null +++ b/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 sha256:699917e74c310be50c0f5e2faf31ed30ff392a1586ef9c1af8dc6b870e6cc191 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc95b6545216d155d3423d0a28bc1e221360856d --- /dev/null +++ b/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 sha256:62e0a1c436e57f4863cd9860228c6f7207e05684bcc93e98f4aa2f752ec40389 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc5ff58fc43ea4e19561aff910a380cf9d6dc61 --- /dev/null +++ b/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 sha256:9735bd2fe9f5f3cd026f77b4184f029f6948c8b09566402150e337dccd1cce07 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5f4a28bfd6b9dacfe5af511198d1c7abd3c83e7 --- /dev/null +++ b/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 sha256:64d0f754fab9823677d2b96d96c829b6df766cde18ced63eda540cfcf5050ba9 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0df432d4bb8f65edede937fa38b0d765643b4c56 --- /dev/null +++ b/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 sha256:77e70a025d3fcb39e814942d5392cee04a0b1687e266d4a4e59b0ddfc76ff5b2 +size 3883031 diff --git a/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c58c56ca77ebdcc9101502a95f25ea6b264177e8 --- /dev/null +++ b/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:e9729ba83eb7ed39da2fe40377e26de6cdce13f43fd7aa20ff06cd8689cabe5e +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5758208a036a1d0407732a9ea288f8e98a728f15 --- /dev/null +++ b/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:f32a46769e9b574812366eab284f299d7f9f9e52d2091e8a959bf0fb6d9761b7 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..88f3e266e6b36006897ab7ed936f9a152fda1b46 --- /dev/null +++ b/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 sha256:57230ab72dcc0168414103c812735e9cc088b08c2e3cd1a7152f2d385a7c7287 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60a37e7326c9ea7d4be9a315ef601e608adeafe4 --- /dev/null +++ b/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 sha256:44202b3257dea72902b900c06049a3fc28d096a309e04053fd6f3417d248ec8d +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4ca1f923f753b4abfc8e13595ffa804860daf90 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6be7a4ad16dad9dc47eecf4be928bf5a87d7aa9aa7ebc5d94e8a0199ed27eb +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c8e73b0d83d798c63e559911573b8bd9d11b20b --- /dev/null +++ b/global_step37905/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:e21e10561a08c0ee65239971809164eba2948a2c24c44581242fbae31b5d0d9d +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9264b25448750a1c56e3a2366864b4e084cfa29 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e44924f027a2b4d287f7122f8d95786fcba49114da7ddd606c273cca664a498 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..affa1bdf22aa6a1bd2d9c6a603210ab1bde08a5c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14488730106b61f79c61ec406bdcbc8b91e5719348c77f37d74dc22fd53ac2bf +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebaeb2708cd23c18a5fa058a698ac01c19dc07a9 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e60a092f7326518b8b0caa6a362589d46b4227197b24a295583a87f6f24e59 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..21c79efc182049a5c02cc5d3a55af0f3445bfa17 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:377f814ca384d2b5393107903b28c4178d0ac4a5ebf64d90d9f76379215e9034 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d56df55323680b303eb908170eec65276a8e8386 --- /dev/null +++ b/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:eb8b3534c1148a4a426fc3fe43f73cc09b1153c4e156abbd3f0fd0775642b09a +size 3883031 diff --git a/global_step37905/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3aebb5df17eb39a01c57f08a3cd1735ce174ebfd --- /dev/null +++ b/global_step37905/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:c27b282c849b4da28df626838277aed46a506c40fe062ecc7a2fbd02e4e58daa +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ccba1894390bbbc70107c9a9217a33790188696 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac5ce27cd8905417fa75e4f11e3c5a9c9041bb89af584ed0b9b0ba84b3c8951 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fcc2fe45131110124a8cebd9964e2a51f0edc835 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a502b9f2913a34a2985d447c2e9f11f02935e3779d4ff899250c965dc3c0ee7 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e185bb72a4e37fc2c3b2d57fbff0fa3d2620cae --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6306693c6a1c799d974d8e79e1f370e725b4679d7e370f245aca39eeb7b532ed +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17609b95a03e352987bb8a9978c998cce5501c71 --- /dev/null +++ b/global_step37905/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:b12fce5593f77cec1d32af374a66d4bbd12820c414329da0f104b45c82826fcc +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..832ea0eac297b29f9f673a54002f057cb7dffde3 --- /dev/null +++ b/global_step37905/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:f834fa26965b555ec65da35b4f6d8d8b8dca1174f48d812439e2112d449e43c2 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d7570de84d26a364748550d50ee0f54f1e8fd69 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c28c770a9a6708e630f187145cd8d9020b47b279198e4022b29dad13546542 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..777a33fd40af81e8fc24a001023f390c5fa6646e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591636556c7a7dad6c4f5660a2bff529b104fff71ded66a1b8df5aa4565993cc +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..60b3c6eb76de5346b1bcdc6a6ccd0d941c958218 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15f71b628b3edac1eab1a2441d20607850657d6f867d65b8a8b0c1bd6e41693c +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..34028eb2ec2eadf23a21bacd14b8f11c0b4c7140 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:920241afdd56ec4826c520ac99439627f10ae9d5ff7b81a038c19292865e99b2 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e42fb6d1d8917b330a99a0fcf20a01b0ff7356f6 --- /dev/null +++ b/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 sha256:3663341b71eef8a4c99bde9adc6d5cd90c38d9febbf5e1e16052115fb71f8cae +size 3883031 diff --git a/global_step37905/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b09d8a3d394fb72010fd3289289e8f9222ace8dc --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8018f7d1f89461b083e9d57f9d9c06319f417b2eb07f32aef47cb8653a76b6a1 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ca20a9a5e684f18f1c3b107f5b62445fcc6972c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba5b29a41579d724327887205c89f6bbf1b9fad9a91f5097b7177140dd1651b +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41149e8198dc25b5efc68af8a4a7753b010ebf1e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772162bd454aa4dbb8b8f694401a3a10987a5d807c1b1393528972a166b45217 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..74f5f10ffec341de279a72e20ac99c07d5b8db0c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e36d893014267a9480298c0d222b472332b1349cf3a0126ebe4d9c480089241 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8469604105ccfd0ca459c81f366e1f772db37168 --- /dev/null +++ b/global_step37905/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:e5c35d212766c46998a939e9ef71f76bc7f50ff656f5eca83f8b52128ac9cd94 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38eb1cf9cfb3d411808b6aa388945c36ee2de22d --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a13350c1f8e244a1edcf1320c54a099976907b087f6d2b0ba49b27538c04764 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..42d48cdd4337aab138eb8d47cb3fc288b93e513c --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f66d02da935f0d1c2ea5f7da2a6fd3c8189bdd9f0d64d21021c285eb2293903 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..38b9f315759fbbe19fb327b8c527c71b7a87820b --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f9465a66079504e70c45c85333ad1a8b70dfbbefeec4f2df398f0f98b56d6b +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e90b8a65f56501b05ed51c17cf6d2b100c060958 --- /dev/null +++ b/global_step37905/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:a0f66be9767ba9be777667c672172eea47fb6d7f530e8aa79f94b7506ca4e28e +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab1a5e6cad951b95edc819ca3537499d0b431240 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8645a83d19858d35e157dc3bb04cfd79a9240e21e058dc662496520bcebcf230 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67bb98a3de20132e26e6cd6c8e506a141fcc008c --- /dev/null +++ b/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 sha256:1cefa219ca4cc7abc2f2ac8b5eacd7055aba90990d83be198af9593720d67d62 +size 3883031 diff --git a/global_step37905/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e73537d682cb6160c08b5a91eb1446ba5abef7e --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9803d419f199dbd4abcfc98fcace67de6d1f67f66dff36ba51ef233ae4d63694 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2af36ef3a471408491c7a5fa6c0452b5a7d6a578 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aa619c6b8d0e58e35749a700d76032ebbc5fcefd2a38da8f46e75740ee706cf +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f7275c8b3d60cd3a6af5c1a5a25a5f10d4c2b68 --- /dev/null +++ b/global_step37905/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:e43a2879c1b9e7c68e98fe3b80ae7117aacfec970c15b54554df24d240919c38 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fe3853318ca251c86a59b5fbfac1a6095daf6cd --- /dev/null +++ b/global_step37905/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:d4ef8f561bfa5ed76d8778cce7365c6fea495eef01bcb4bdbfadf9f563c9f304 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc309f0469c4cd138af9eb8cbda20a321a310af7 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e33e94831215361491f00cd2e2df0f73852752ddd2071d7b13240ab84760ea1 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..67577030723c79785da1af7cf9c2c237c378d021 --- /dev/null +++ b/global_step37905/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:aed8865ccc9071b446300f467ce865a5fbbd622a7b31d014e481496a63d5d86f +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ffc7a84c25f4b6c3f778f21b0e1cfbdc8f71b603 --- /dev/null +++ b/global_step37905/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:d64ae174d79fbef7087c55598ed80177300c1a654078793023a385d3d5bbd533 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a51c86cc09ba3e502ff10d39d4e3045a93a4c66d --- /dev/null +++ b/global_step37905/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:b3191414e79f9c089abeb51ea03cd2c9b5e3769c6be0bd0604f337f460aa4853 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7210e2a25b50f707c4e11ce97bea3abde1eabb23 --- /dev/null +++ b/global_step37905/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:e223614e17fc4ec25da9891d32d5a9a92c6c63edfdced10226298d6b6d6deeb1 +size 3883106 diff --git a/global_step37905/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..72441a9c631265b41c395335393a4b7246eef6a2 --- /dev/null +++ b/global_step37905/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d45ed4b4ab1762a76da14482eb8654748a6e33fc38244e2186de90c911456f4 +size 3883042 diff --git a/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ffe7612b315786e01d16b54c8589dd8eb60fec6 --- /dev/null +++ b/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:be1ba6683b78059776c1f9a9dd989e103f91e2cbe5ba78af483af96bd43c8ab4 +size 3883095 diff --git a/global_step37905/layer_01-model_00-model_states.pt b/global_step37905/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9b613557d5d584ea6698ab8fb979447dfd94238 --- /dev/null +++ b/global_step37905/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a8106a1483a21d1a7224619dc0a1e53ca64b6aef9a0132d1c47ac1a3a8aa34 +size 67011843 diff --git a/global_step37905/layer_03-model_00-model_states.pt b/global_step37905/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca6350787e41cf9b11387de819391a3966316ff5 --- /dev/null +++ b/global_step37905/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830eba4df290afdf8029d40c6922f82c9c55dee40948b615a5f7ea1a161f3b8b +size 9851395 diff --git a/global_step37905/layer_04-model_00-model_states.pt b/global_step37905/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad9c6ab1267221afdd813bdba40ec5afae4b205d --- /dev/null +++ b/global_step37905/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a489ef5038954ec73a4686ecfb4bf169e84286c7832822e60dd29290d7c524 +size 9851395 diff --git a/global_step37905/layer_05-model_00-model_states.pt b/global_step37905/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..753829174f5cdf5d95bf350e66dfc60afdeb0f99 --- /dev/null +++ b/global_step37905/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494b853fe25d326b59817af4c1a9f0f993898f7faa6819b093a498e908dad02f +size 9851395 diff --git a/global_step37905/layer_06-model_00-model_states.pt b/global_step37905/layer_06-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e66d5d847f3f88cded982b442f752f1df21624c4 --- /dev/null +++ b/global_step37905/layer_06-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50e694e301ad3f4197e671975bed419714ff0aedf6a2756b8d401d6b976c40f1 +size 9851395 diff --git a/global_step37905/layer_07-model_00-model_states.pt b/global_step37905/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b50784f66b9894ccdcfedc53c17b02f4cfb6296 --- /dev/null +++ b/global_step37905/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e349367ebe63e668122b9214d231d7a5e5638b97d25f043e7bad079d07809eac +size 9851395 diff --git a/global_step37905/layer_08-model_00-model_states.pt b/global_step37905/layer_08-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c217fe1d957ee5317d8446c70d984fd64990d45 --- /dev/null +++ b/global_step37905/layer_08-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc7497e41a1c8a85d48df87070d5efe315def2aeaeac4bc01a1ceb42ef1d0db8 +size 9851395 diff --git a/global_step37905/layer_09-model_00-model_states.pt b/global_step37905/layer_09-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5bf4b5e7829d574a6d19da41db8ac71b335c6d32 --- /dev/null +++ b/global_step37905/layer_09-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c00b81400ee25a938a890531e5f148459f21754d31e5a569aad1e56e2907c41 +size 9851395 diff --git a/global_step37905/layer_10-model_00-model_states.pt b/global_step37905/layer_10-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a73cd0991d2bcb1023a1d8cb93fb4396dce4f2d --- /dev/null +++ b/global_step37905/layer_10-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd7a87ab682c67358f6574f5634312b053cde91ebb54baec5206438cca1f200 +size 9851395 diff --git a/global_step37905/layer_11-model_00-model_states.pt b/global_step37905/layer_11-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2a72bc7d7aadc0e1a02427a7e1a63f1543fed5f --- /dev/null +++ b/global_step37905/layer_11-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4124c972e74d79ed9783a149ef0cca283533452dee5dd00e73595989e2bde23 +size 9851395 diff --git a/global_step37905/layer_12-model_00-model_states.pt b/global_step37905/layer_12-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d9c2c946955966d879bbf1575b60523c349319a --- /dev/null +++ b/global_step37905/layer_12-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ebdf4a2bc637191fedafa955e2027cdb1a86f76a09810eab896b55a91e09a6 +size 9851395 diff --git a/global_step37905/layer_14-model_00-model_states.pt b/global_step37905/layer_14-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa3b54bbc5a271e73877fee636289c22f0332e11 --- /dev/null +++ b/global_step37905/layer_14-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74817f9cdb75a8c7f4484ecf154d4d56f97576150cc4c2121c00bb01c216fc4f +size 3779 diff --git a/global_step37905/mp_rank_00_model_states.pt b/global_step37905/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8eebcb25391c718a9b32bd085db9fa72a972a67d --- /dev/null +++ b/global_step37905/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ab507b92a4b4aec27a458add2db9098db3a3aee6da1979f817652b017f34a1 +size 31347 diff --git a/logs/2058110_118.err b/logs/2058110_118.err new file mode 100644 index 0000000000000000000000000000000000000000..840d2cb5bc4733bcf85324b4ef0bf7d65065131d --- /dev/null +++ b/logs/2058110_118.err @@ -0,0 +1,1846 @@ +20: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +20: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +20: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +21: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +21: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +21: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +23: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +23: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +23: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +19: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': 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 + 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. +31: Successfully preprocessed all matching files. +31: Successfully preprocessed all matching files. +31: Successfully preprocessed all matching files. +18: Successfully preprocessed all matching files. +31: Successfully preprocessed all matching files. + 2: Successfully preprocessed all matching files. +28: Successfully preprocessed all matching files. + 3: Successfully preprocessed all matching files. +14: Successfully preprocessed all matching files. +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( +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( +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( + 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( +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( +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( +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( +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( + 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( +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( +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( + 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( + 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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( + 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( +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( +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( + 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( + 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( + 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( +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( +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( +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( +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( +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( +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( +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( + 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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( + 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( +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( + 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( +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( +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( + 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( + 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( +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( + 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( + 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( +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( +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( + 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( +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( + 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( +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( +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( +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( + 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( +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( +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( +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( +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( + 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( + 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( +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( +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( + 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( +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( + 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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( + 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( +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( + 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( +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( + 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( +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( +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( + 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( +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( + 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( + 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( +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( +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( +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( + 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( +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( +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( +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( + 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( +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( +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( +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( + 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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( +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( + 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( +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( +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( + 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( +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( + 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( +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( +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( +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( +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( + 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( +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( +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( + 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( +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( + 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( +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( +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( +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( + 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( +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( + 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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( + 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( +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( + 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( +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( + 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( +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( + 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( +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( +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( + 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( +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( +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( +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( + 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( +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( +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( +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( +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( + 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( +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( +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( + 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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( + 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( +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( +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( +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( + 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( +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( + 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( +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( + 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... + 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... + 7: 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... +11: 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... +21: 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... +15: 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... +26: 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... + 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... + 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... + 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... + 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... + 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: 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... + 3: + 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: + 5: 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... + 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... + 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... + 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... + 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: + 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... + 9: 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... + 9: 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... +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: +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... +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... +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... +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... +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... +11: 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...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... +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... +13: 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... +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... +15: 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... +15: 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... +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... +13: 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... +15: +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... +15: +13: 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... +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: 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... +13: 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... +13: 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... +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... +17: 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: 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: Using /pfs/lustrep4/users/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: 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... +19: +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... +19: +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... +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: 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... +21: 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +21: 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: 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: 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... +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... +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... +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... +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: 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... +23: +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... +24: 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... +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... +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... +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... +24: 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... +25: 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... +25: 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... +26: 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... +25: 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... +26: 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... +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... +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... +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... +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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: 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... +28: 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... +29: 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... +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: +29: 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... +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... +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... +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... +30: 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... +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... + 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... +26: 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... +26: Loading extension module utils... +26: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +26: Loading extension module utils... +25: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +28: 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... +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: 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... +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... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +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... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: 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...No modifications detected for re-loaded extension module utils, skipping build step... +25: +25: Loading extension module utils... +25: 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... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +25: 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... +25: No modifications detected for re-loaded extension module utils, skipping build step... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +25: Loading extension module utils... +25: 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... +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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: 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... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: 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: +26: 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... +26: 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... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +26: 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... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: 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: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +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: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +29: 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... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... + 0: Loading extension module utils... + 0: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Loading extension module utils... + 0: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +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... + 2: 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... +30: Loading extension module utils... +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: 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... + 2: Loading extension module utils... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... +30: Loading extension module utils... +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... + 2: 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...No modifications detected for re-loaded extension module utils, skipping build step... +30: +30: Loading extension module utils...Loading extension module utils... +30: +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... + 2: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... + 4: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils... + 2: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 1: Loading extension module utils... + 1: Loading extension module utils... +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: + 1: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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: + 1: Loading extension module utils... +31: Loading extension module utils...Loading extension module utils... +31: +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 1: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... + 4: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 4: 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... + 3: Loading extension module utils... + 3: Loading extension module utils... + 4: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... + 5: Loading extension module utils... + 6: 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... + 5: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 5: Loading extension module utils... + 7: 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... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: Loading extension module utils... +28: 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... +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... +28: +28: +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... + 7: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: 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... +28: +28: +28: Loading extension module utils...Loading extension module utils...Loading extension module utils... +28: +28: + 7: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +28: +28: Loading extension module utils...Loading extension module utils... +28: +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... + 7: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 8: Loading extension module utils... + 9: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 9: Loading extension module utils... + 8: Loading extension module utils... + 9: Loading extension module utils... + 8: Loading extension module utils... + 9: Loading extension module utils... + 8: Loading extension module utils... + 9: Loading extension module utils... + 8: Loading extension module utils... +11: Loading extension module utils... + 8: 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... +11: Loading extension module utils... +10: Loading extension module utils... +11: Loading extension module utils... +10: 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... +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... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +16: 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... +14: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +14: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +14: Loading extension module utils... +13: Loading extension module utils... + 0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: Loading extension module utils... + 0: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +14: 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... + 0: +14: 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: +14: Loading extension module utils... +15: Loading extension module utils... +14: Loading extension module utils... +13: Loading extension module utils... +15: Loading extension module utils... +16: Loading extension module utils... +13: Loading extension module utils... +16: Loading extension module utils... +13: Loading extension module utils... +15: Loading extension module utils... +16: Loading extension module utils... +13: Loading extension module utils... +15: Loading extension module utils... +16: Loading extension module utils... +15: Loading extension module utils... +13: Loading extension module utils... +15: Loading extension module utils... +13: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +16: 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... +16: 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... + 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: 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: 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... + 4: 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: No modifications detected for re-loaded extension module utils, skipping build step... + 1: 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... + 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: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 4: + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 4: 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: 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... + 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... + 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... + 4: Loading extension module utils... + 4: 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: +17: 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... + 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: 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: +17: Loading extension module utils... + 2: Loading extension module utils...Loading extension module utils... + 2: + 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... + 4: Loading extension module utils... +17: Loading extension module utils... + 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... + 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... +17: 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... +18: Loading extension module utils... +17: 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... +17: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... + 3: Loading extension module utils... +17: 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... +17: 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: 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: Loading extension module utils... + 3: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... + 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... +18: Loading extension module utils... +21: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Loading extension module utils... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: Loading extension module utils... + 6: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: 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... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... +14: 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: Using /pfs/lustrep4/users/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: + 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... + 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: + 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... + 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... + 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... + 7: 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: 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... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 5: 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... + 7: 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... + 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... + 6: Loading extension module utils... +20: Loading extension module utils... + 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: 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: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 7: + 7: 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... + 7: 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... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 6: Loading extension module utils... + 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... + 7: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: 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... +23: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +19: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +19: Loading extension module utils... +21: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +19: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +21: Loading extension module utils... +19: Loading extension module utils... +21: Loading extension module utils... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: 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: 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... +22: Loading extension module utils... + 9: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Loading extension module utils... + 8: 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: 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: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... + 9: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +23: Loading extension module utils... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Loading extension module utils... +22: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Loading extension module utils... + 8: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +23: Loading extension module utils... +22: 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: Loading extension module utils... + 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: +22: Loading extension module utils... +22: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: 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... +22: Loading extension module utils... + 8: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 8: + 8: Loading extension module utils...Loading extension module utils... + 8: +22: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +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... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: 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... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +10: 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... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +10: +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +10: Loading extension module utils... +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... +10: 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... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +11: 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... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +10: 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... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +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: 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... +12: 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... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +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: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: 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... +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... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +16: 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... +16: 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... +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: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +16: 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... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: 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... +14: 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... +14: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +14: +14: Loading extension module utils...Loading extension module utils... +14: +16: 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... +16: No modifications detected for re-loaded extension module utils, skipping build step... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +16: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +14: 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... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +15: 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... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: 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... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: 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: 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...Loading extension module utils... +15: +15: No modifications detected for re-loaded extension module utils, skipping build step... +14: 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...Loading extension module utils... +15: +14: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +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... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +17: 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... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +13: 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... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +13: 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... +13: 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... +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... +13: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +17: +17: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +13: 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... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: 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: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +17: +17: Loading extension module utils...Loading extension module utils... +17: +17: 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... +17: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +21: 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... +13: 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... +14: 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... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +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: 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...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... +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... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +21: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +20: 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... +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: 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... +21: 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... +21: 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... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +20: 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... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +21: 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... +21: No modifications detected for re-loaded extension module utils, skipping build step...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +21: +21: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +20: 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... +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... +21: 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... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: 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... +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: 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: Loading extension module utils...Loading extension module utils... +19: +23: 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... +19: +19: +23: 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... +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...Loading extension module utils... +19: +19: +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: 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... +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +19: +19: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +19: +19: +23: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: Loading extension module utils... +23: 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... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: 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... +23: 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... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: 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") + 0: slurmstepd: error: *** STEP 2058110.25 ON nid005360 CANCELLED AT 2022-11-24T16:24:06 *** diff --git a/logs/2058110_118.out b/logs/2058110_118.out new file mode 100644 index 0000000000000000000000000000000000000000..1baf67109a5d17882b4cc5f171b5c6544a8e4756 --- /dev/null +++ b/logs/2058110_118.out @@ -0,0 +1,43705 @@ + 0: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 2: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +14: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 0: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +14: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 6: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +13: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 4: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +20: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +26: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +21: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 0: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +18: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 0: START 2058110: Thu Nov 24 14:12:07 EET 2022 +14: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +14: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 3: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 8: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +24: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +23: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +17: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +11: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 9: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +12: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +31: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 5: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +28: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +27: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +30: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +16: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +22: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 7: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +15: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +25: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 1: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +29: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +19: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +10: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 2: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 2: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 2: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 6: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 6: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 6: START 2058110: Thu Nov 24 14:12:07 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 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 2 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 4 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 7 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: ================================================================================ + 0: ============================= End of ROCm SMI Log ============================== +13: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +13: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +13: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 4: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 4: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 4: START 2058110: Thu Nov 24 14:12:07 EET 2022 +20: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +20: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +20: START 2058110: Thu Nov 24 14:12:07 EET 2022 +26: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +26: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +26: START 2058110: Thu Nov 24 14:12:07 EET 2022 +21: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +21: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +21: START 2058110: Thu Nov 24 14:12:07 EET 2022 +18: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +18: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +14: +14: +14: ======================= ROCm System Management Interface ======================= +14: ================================= Concise Info ================================= +14: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +14: 0 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 2 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 4 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 6 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: ================================================================================ +14: ============================= End of ROCm SMI Log ============================== +18: START 2058110: Thu Nov 24 14:12:07 EET 2022 +31: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +31: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +31: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 8: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 8: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 8: START 2058110: Thu Nov 24 14:12:07 EET 2022 +28: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +28: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +28: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 5: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 5: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 5: START 2058110: Thu Nov 24 14:12:07 EET 2022 +27: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +27: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +27: START 2058110: Thu Nov 24 14:12:07 EET 2022 +30: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +30: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +30: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 3: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 3: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 3: START 2058110: Thu Nov 24 14:12:07 EET 2022 +24: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +24: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +24: START 2058110: Thu Nov 24 14:12:07 EET 2022 +23: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +23: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +23: START 2058110: Thu Nov 24 14:12:07 EET 2022 +17: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +17: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +17: START 2058110: Thu Nov 24 14:12:07 EET 2022 +16: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +16: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +11: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +11: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +16: START 2058110: Thu Nov 24 14:12:07 EET 2022 +11: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 9: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 9: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 9: START 2058110: Thu Nov 24 14:12:07 EET 2022 +12: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +12: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +12: START 2058110: Thu Nov 24 14:12:07 EET 2022 +22: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +22: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +22: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 7: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 7: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 7: START 2058110: Thu Nov 24 14:12:07 EET 2022 +25: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +25: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +15: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +15: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +25: START 2058110: Thu Nov 24 14:12:07 EET 2022 +15: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 1: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 1: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 1: START 2058110: Thu Nov 24 14:12:07 EET 2022 +29: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +29: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +29: START 2058110: Thu Nov 24 14:12:07 EET 2022 +19: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +19: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +10: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +19: START 2058110: Thu Nov 24 14:12:07 EET 2022 +10: START 2058110: Thu Nov 24 14:12:07 EET 2022 + 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 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 1 55.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 2 39.0c 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 46.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 6 44.0c 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 47.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 2 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 4 46.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 5 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 6 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: ================================================================================ + 6: ============================= 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 50.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 2 40.0c 86.0W 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 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 6 39.0c 88.0W 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 ============================== + 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 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 2 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 3 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 4 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 6 43.0c 90.0W 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 ============================== +20: +20: +20: ======================= ROCm System Management Interface ======================= +20: ================================= Concise Info ================================= +20: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +20: 0 49.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 2 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 4 48.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 6 45.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: ================================================================================ +20: ============================= 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 54.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 2 43.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 4 46.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 6 41.0c 92.0W 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 ============================== +21: +21: +21: ======================= ROCm System Management Interface ======================= +21: ================================= Concise Info ================================= +21: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +21: 0 50.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 2 39.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 4 47.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 5 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 6 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: ================================================================================ +21: ============================= 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 51.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 1 54.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 2 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 4 48.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 6 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: ================================================================================ +31: ============================= 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 46.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 2 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 3 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 4 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 6 48.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: ================================================================================ +18: ============================= 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 46.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 2 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 4 41.0c 99.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 5 57.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 6 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: ================================================================================ + 8: ============================= 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 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 2 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 3 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 4 47.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 6 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: ================================================================================ +28: ============================= 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 51.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 2 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 4 46.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 6 43.0c 89.0W 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 ============================== +27: +27: +27: ======================= ROCm System Management Interface ======================= +27: ================================= Concise Info ================================= +27: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +27: 0 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 2 44.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 4 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 6 50.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: ================================================================================ +27: ============================= 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 48.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 2 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 4 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 6 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: ================================================================================ +30: ============================= 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 47.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 2 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 4 46.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 5 57.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 6 46.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: ================================================================================ +24: ============================= 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 51.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 2 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 4 43.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 6 47.0c 88.0W 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 ============================== +17: +17: +17: ======================= ROCm System Management Interface ======================= +17: ================================= Concise Info ================================= +17: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +17: 0 49.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 2 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 4 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 6 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: ================================================================================ +17: ============================= 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 52.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 2 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 4 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 5 55.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 6 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: ================================================================================ +23: ============================= 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 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 2 36.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 4 49.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 6 47.0c 88.0W 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 ============================== +11: +11: +11: ======================= ROCm System Management Interface ======================= +11: ================================= Concise Info ================================= +11: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +11: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 2 43.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 4 50.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 6 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 7 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: ================================================================================ +11: ============================= 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 51.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 2 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 4 49.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 6 48.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: ================================================================================ + 9: ============================= 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 51.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 2 47.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 4 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 5 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 6 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: ================================================================================ +22: ============================= 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 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 2 47.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 4 47.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 6 47.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 7 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: ================================================================================ +12: ============================= 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 54.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 2 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 4 52.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 6 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: ================================================================================ + 7: ============================= 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 49.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 2 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 4 50.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 6 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: ================================================================================ +25: ============================= 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 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 1 56.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 2 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 4 47.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 6 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: ================================================================================ +15: ============================= 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 54.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 1 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 2 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 4 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 5 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 6 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: ================================================================================ +29: ============================= 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 48.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 2 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 4 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 6 42.0c 88.0W 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 ============================== +19: +19: +19: ======================= ROCm System Management Interface ======================= +19: ================================= Concise Info ================================= +19: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +19: 0 51.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 2 48.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 4 48.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 6 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: ================================================================================ +19: ============================= 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 46.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 2 44.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 4 49.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 6 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: ================================================================================ +10: ============================= End of ROCm SMI Log ============================== + 6: Launching on nid005366 (6/32), master nid005360 port 9999, GPUs 8, CUDA: True +28: Launching on nid005420 (28/32), master nid005360 port 9999, GPUs 8, CUDA: True +24: Launching on nid005416 (24/32), master nid005360 port 9999, GPUs 8, CUDA: True + 4: Launching on nid005364 (4/32), master nid005360 port 9999, GPUs 8, CUDA: True + 0: Launching on nid005360 (0/32), master nid005360 port 9999, GPUs 8, CUDA: True + 5: Launching on nid005365 (5/32), master nid005360 port 9999, GPUs 8, CUDA: True +15: Launching on nid005396 (15/32), master nid005360 port 9999, GPUs 8, CUDA: True +12: Launching on nid005372 (12/32), master nid005360 port 9999, GPUs 8, CUDA: True + 1: Launching on nid005361 (1/32), master nid005360 port 9999, GPUs 8, CUDA: True +29: Launching on nid005421 (29/32), master nid005360 port 9999, GPUs 8, CUDA: True +13: Launching on nid005373 (13/32), master nid005360 port 9999, GPUs 8, CUDA: True +25: Launching on nid005417 (25/32), master nid005360 port 9999, GPUs 8, CUDA: True +11: Launching on nid005371 (11/32), master nid005360 port 9999, GPUs 8, CUDA: True +27: Launching on nid005419 (27/32), master nid005360 port 9999, GPUs 8, CUDA: True +21: Launching on nid005413 (21/32), master nid005360 port 9999, GPUs 8, CUDA: True +31: Launching on nid005423 (31/32), master nid005360 port 9999, GPUs 8, CUDA: True + 8: Launching on nid005368 (8/32), master nid005360 port 9999, GPUs 8, CUDA: True +22: Launching on nid005414 (22/32), master nid005360 port 9999, GPUs 8, CUDA: True +14: Launching on nid005395 (14/32), master nid005360 port 9999, GPUs 8, CUDA: True + 9: Launching on nid005369 (9/32), master nid005360 port 9999, GPUs 8, CUDA: True +17: Launching on nid005398 (17/32), master nid005360 port 9999, GPUs 8, CUDA: True +19: Launching on nid005411 (19/32), master nid005360 port 9999, GPUs 8, CUDA: True + 7: Launching on nid005367 (7/32), master nid005360 port 9999, GPUs 8, CUDA: True +16: Launching on nid005397 (16/32), master nid005360 port 9999, GPUs 8, CUDA: True +23: Launching on nid005415 (23/32), master nid005360 port 9999, GPUs 8, CUDA: True +30: Launching on nid005422 (30/32), master nid005360 port 9999, GPUs 8, CUDA: True +10: Launching on nid005370 (10/32), master nid005360 port 9999, GPUs 8, CUDA: True + 3: Launching on nid005363 (3/32), master nid005360 port 9999, GPUs 8, CUDA: True +26: Launching on nid005418 (26/32), master nid005360 port 9999, GPUs 8, CUDA: True +18: Launching on nid005399 (18/32), master nid005360 port 9999, GPUs 8, CUDA: True +20: Launching on nid005412 (20/32), master nid005360 port 9999, GPUs 8, CUDA: True + 2: Launching on nid005362 (2/32), master nid005360 port 9999, GPUs 8, CUDA: True + 0: using world size: 256, data-parallel-size: 256, 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 .............................. 256 + 0: data_path ....................................... ['/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_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/2058110.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-1 + 0: kv_channels ..................................... 64 + 0: layer_norm_fusion ............................... True + 0: layernorm_epsilon ............................... 1e-05 + 0: lazy_mpu_init ................................... None + 0: load ............................................ checkpoints_83m + 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 ............................... 0 + 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 ............................. 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_83m + 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_83m + 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 ...................................... 256 + 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: [2022-11-24 14:12:16,448] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +31: > 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: 0.057 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: 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: 24.223 seconds + 0: time to initialize megatron (seconds): 70.222 + 0: [after megatron is initialized] datetime: 2022-11-24 14:12:54 + 0: building GPT model ... + 0: [2022-11-24 14:12:54,277] [INFO] [utils.py:827:see_memory_usage] Before Building Model + 0: [2022-11-24 14:12:54,278] [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: [2022-11-24 14:12:54,278] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.09 GB, percent = 6.8% + 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, 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} + 0: [2022-11-24 14:13:03,467] [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: [2022-11-24 14:13:03,554] [INFO] [utils.py:827:see_memory_usage] After Building Model + 0: [2022-11-24 14:13:03,554] [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: [2022-11-24 14:13:03,554] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.1 GB, percent = 6.8% + 0: setting training iterations to 37905 + 0: > learning rate decay style: cosine + 0: DeepSpeed is enabled. + 0: [2022-11-24 14:13:03,556] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown + 0: [2022-11-24 14:13:22,515] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False + 0: [2022-11-24 14:13:22,516] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer + 0: [2022-11-24 14:13:22,516] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer + 0: [2022-11-24 14:13:22,518] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam + 0: [2022-11-24 14:13:22,518] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer + 0: [2022-11-24 14:13:22,564] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer + 0: [2022-11-24 14:13:22,565] [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: [2022-11-24 14:13:22,565] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.81 GB, percent = 6.9% + 0: ninja: no work to do. + 0: Time to load utils op: 0.1434478759765625 seconds + 0: Time to load utils op: 0.10196900367736816 seconds + 0: [2022-11-24 14:13:22,710] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 + 0: [2022-11-24 14:13:22,711] [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: [2022-11-24 14:13:22,711] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.8 GB, percent = 6.9% + 0: [2022-11-24 14:13:22,756] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 + 0: [2022-11-24 14:13:22,757] [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: [2022-11-24 14:13:22,757] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.81 GB, percent = 6.9% + 0: [2022-11-24 14:13:22,791] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 + 0: [2022-11-24 14:13:22,792] [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: [2022-11-24 14:13:22,792] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.81 GB, percent = 6.9% + 0: [2022-11-24 14:13:22,831] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 + 0: [2022-11-24 14:13:22,832] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 14:13:22,832] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.81 GB, percent = 6.9% + 0: ninja: no work to do. + 0: Time to load utils op: 0.13348889350891113 seconds +26: Time to load utils op: 0.30415892601013184 seconds +24: Time to load utils op: 0.10231423377990723 secondsTime to load utils op: 0.1018528938293457 seconds +24: +24: Time to load utils op: 0.10303783416748047 seconds +24: Time to load utils op: 0.10176396369934082 seconds +24: Time to load utils op: 0.10231590270996094 seconds +24: Time to load utils op: 0.10274696350097656 seconds +24: Time to load utils op: 0.10217046737670898 seconds +24: Time to load utils op: 0.10229897499084473 seconds +26: Time to load utils op: 0.10182929039001465 seconds +26: Time to load utils op: 0.10159754753112793 seconds +25: Time to load utils op: 0.10180950164794922 secondsTime to load utils op: 0.10316658020019531 seconds +25: +25: Time to load utils op: 0.10199737548828125 seconds +25: Time to load utils op: 0.10211992263793945 secondsTime to load utils op: 0.10305452346801758 seconds +25: +26: Time to load utils op: 0.10162782669067383 seconds +26: Time to load utils op: 0.10164332389831543 secondsTime to load utils op: 0.1020209789276123 seconds +26: +25: Time to load utils op: 0.10268044471740723 seconds +26: Time to load utils op: 0.10160303115844727 seconds +25: Time to load utils op: 0.1020040512084961 seconds +25: Time to load utils op: 0.10289645195007324 seconds +26: Time to load utils op: 0.10156822204589844 seconds +27: Time to load utils op: 0.10296082496643066 seconds +27: Time to load utils op: 0.1017143726348877 seconds +27: Time to load utils op: 0.1023552417755127 seconds +27: Time to load utils op: 0.10273885726928711 seconds +27: Time to load utils op: 0.10346531867980957 seconds +27: Time to load utils op: 0.10270953178405762 seconds +27: Time to load utils op: 0.10260415077209473 seconds +27: Time to load utils op: 0.10242033004760742 seconds +29: Time to load utils op: 0.10264754295349121 seconds +29: Time to load utils op: 0.1023554801940918 seconds +29: Time to load utils op: 0.10280251502990723 seconds +29: Time to load utils op: 0.10382723808288574 seconds +29: Time to load utils op: 0.10381197929382324 seconds +29: Time to load utils op: 0.10314655303955078 seconds +29: Time to load utils op: 0.10393953323364258 seconds +29: Time to load utils op: 0.10288119316101074 seconds +30: Time to load utils op: 0.10206151008605957 secondsTime to load utils op: 0.10199642181396484 seconds +30: +30: Time to load utils op: 0.10313868522644043 seconds +30: Time to load utils op: 0.1022183895111084 seconds +30: Time to load utils op: 0.10306572914123535 seconds +30: Time to load utils op: 0.10314607620239258 seconds +30: Time to load utils op: 0.1022951602935791 seconds +30: Time to load utils op: 0.10321736335754395 seconds +31: Time to load utils op: 0.10355520248413086 seconds +31: Time to load utils op: 0.10309863090515137 seconds +31: Time to load utils op: 0.10269951820373535 seconds +31: Time to load utils op: 0.10385894775390625 seconds +31: Time to load utils op: 0.10390949249267578 seconds +31: Time to load utils op: 0.10336184501647949 seconds +31: Time to load utils op: 0.10415816307067871 seconds +31: Time to load utils op: 0.10342168807983398 seconds + 0: [2022-11-24 14:13:22,868] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 + 0: [2022-11-24 14:13:22,868] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 14:13:22,869] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.81 GB, percent = 6.9% +28: Time to load utils op: 0.11316084861755371 seconds +28: Time to load utils op: 0.11324095726013184 seconds +28: Time to load utils op: 0.11333966255187988 seconds +28: Time to load utils op: 0.11340475082397461 seconds +28: Time to load utils op: 0.11313247680664062 seconds +28: Time to load utils op: 0.11311459541320801 seconds +28: Time to load utils op: 0.11341094970703125 seconds +28: Time to load utils op: 0.11368608474731445 seconds + 0: Time to load utils op: 0.0006806850433349609 seconds + 0: Time to load utils op: 0.0005276203155517578 seconds + 0: [2022-11-24 14:13:22,908] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 + 0: [2022-11-24 14:13:22,908] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 14:13:22,908] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.83 GB, percent = 6.9% +24: Time to load utils op: 0.00046443939208984375 seconds +24: Time to load utils op: 0.00035572052001953125 seconds +24: Time to load utils op: 0.00032591819763183594 seconds +26: Time to load utils op: 0.0006411075592041016 seconds +24: Time to load utils op: 0.0003502368927001953 seconds +24: Time to load utils op: 0.00034499168395996094 seconds +24: Time to load utils op: 0.00034427642822265625 seconds +24: Time to load utils op: 0.00033092498779296875 seconds +24: Time to load utils op: 0.0003139972686767578 seconds +25: Time to load utils op: 0.0004506111145019531 seconds +25: Time to load utils op: 0.0003561973571777344 seconds +25: Time to load utils op: 0.0003478527069091797 seconds +26: Time to load utils op: 0.0003266334533691406 seconds +25: Time to load utils op: 0.00034999847412109375 seconds +26: Time to load utils op: 0.0003941059112548828 seconds +25: Time to load utils op: 0.0003211498260498047 seconds +25: Time to load utils op: 0.00035762786865234375 seconds +25: Time to load utils op: 0.00034165382385253906 seconds +25: Time to load utils op: 0.00030994415283203125 seconds +26: Time to load utils op: 0.00033283233642578125 seconds +26: Time to load utils op: 0.0004017353057861328 seconds +26: Time to load utils op: 0.0003807544708251953 seconds +27: Time to load utils op: 0.0004317760467529297 seconds +26: Time to load utils op: 0.0003769397735595703 seconds +26: Time to load utils op: 0.0003993511199951172 seconds +27: Time to load utils op: 0.0003223419189453125 seconds +27: Time to load utils op: 0.0003993511199951172 secondsTime to load utils op: 0.000392913818359375 seconds +27: +27: Time to load utils op: 0.0003635883331298828 seconds +27: Time to load utils op: 0.0003733634948730469 seconds +27: Time to load utils op: 0.0003311634063720703 seconds +27: Time to load utils op: 0.000377655029296875 seconds +29: Time to load utils op: 0.0004355907440185547 seconds +29: Time to load utils op: 0.0003116130828857422 seconds +29: Time to load utils op: 0.0003323554992675781 seconds +29: Time to load utils op: 0.0003924369812011719 seconds +29: Time to load utils op: 0.00036334991455078125 seconds +29: Time to load utils op: 0.0003650188446044922 seconds +29: Time to load utils op: 0.0003657341003417969 seconds +29: Time to load utils op: 0.00040435791015625 seconds +30: Time to load utils op: 0.0004723072052001953 seconds + 0: Time to load utils op: 0.20225977897644043 seconds + 0: Time to load utils op: 0.20282888412475586 seconds + 0: Time to load utils op: 0.20240068435668945 seconds +30: Time to load utils op: 0.00034999847412109375 seconds +30: Time to load utils op: 0.0003528594970703125 seconds + 0: Time to load utils op: 0.20288753509521484 seconds + 0: Time to load utils op: 0.20218729972839355 seconds +30: Time to load utils op: 0.0003020763397216797 seconds +30: Time to load utils op: 0.00030875205993652344 seconds +30: Time to load utils op: 0.00034356117248535156 seconds +30: Time to load utils op: 0.0003592967987060547 seconds +30: Time to load utils op: 0.0003337860107421875 seconds +31: Time to load utils op: 0.0004596710205078125 seconds +31: Time to load utils op: 0.00042438507080078125 seconds +31: Time to load utils op: 0.000331878662109375 seconds + 2: Time to load utils op: 0.20287775993347168 secondsTime to load utils op: 0.4042658805847168 seconds + 2: + 2: Time to load utils op: 0.20265626907348633 seconds + 2: Time to load utils op: 0.2027120590209961 seconds + 2: Time to load utils op: 0.20209050178527832 seconds + 2: Time to load utils op: 0.20191144943237305 seconds + 2: Time to load utils op: 0.20217037200927734 seconds +31: Time to load utils op: 0.00038433074951171875 secondsTime to load utils op: 0.00038623809814453125 seconds +31: +31: Time to load utils op: 0.00035834312438964844 seconds + 1: Time to load utils op: 0.2042386531829834 seconds +31: Time to load utils op: 0.00035643577575683594 seconds + 1: Time to load utils op: 0.20407915115356445 seconds + 1: Time to load utils op: 0.2039504051208496 seconds + 2: Time to load utils op: 0.20230412483215332 seconds + 1: Time to load utils op: 0.20445823669433594 secondsTime to load utils op: 0.20371365547180176 seconds + 1: + 4: Time to load utils op: 0.4032926559448242 seconds + 1: Time to load utils op: 0.204359769821167 seconds + 1: Time to load utils op: 0.2046518325805664 seconds +31: Time to load utils op: 0.0003006458282470703 seconds + 1: Time to load utils op: 0.20406770706176758 seconds + 3: Time to load utils op: 0.2027757167816162 seconds + 4: Time to load utils op: 0.20184826850891113 seconds + 4: Time to load utils op: 0.20234942436218262 secondsTime to load utils op: 0.20246052742004395 seconds + 4: + 3: Time to load utils op: 0.2027115821838379 seconds + 3: Time to load utils op: 0.20296001434326172 seconds + 3: Time to load utils op: 0.20292139053344727 seconds + 4: Time to load utils op: 0.20216751098632812 secondsTime to load utils op: 0.20216941833496094 seconds + 4: + 4: Time to load utils op: 0.20178580284118652 seconds + 3: Time to load utils op: 0.2038586139678955 secondsTime to load utils op: 0.2044532299041748 secondsTime to load utils op: 0.20343303680419922 seconds + 3: + 3: + 4: Time to load utils op: 0.20195317268371582 seconds + 3: Time to load utils op: 0.2045154571533203 seconds + 6: Time to load utils op: 0.40396904945373535 seconds + 5: Time to load utils op: 0.20357418060302734 seconds + 5: Time to load utils op: 0.2026383876800537 seconds + 5: Time to load utils op: 0.20273470878601074 seconds + 6: Time to load utils op: 0.20212721824645996 seconds + 6: Time to load utils op: 0.20190834999084473 seconds + 5: Time to load utils op: 0.20262765884399414 seconds + 5: Time to load utils op: 0.2023773193359375 seconds +28: Time to load utils op: 0.0004475116729736328 seconds + 6: Time to load utils op: 0.20210480690002441 secondsTime to load utils op: 0.20206999778747559 secondsTime to load utils op: 0.2016305923461914 seconds + 6: + 6: + 5: Time to load utils op: 0.20309972763061523 seconds + 5: Time to load utils op: 0.20343661308288574 secondsTime to load utils op: 0.20306754112243652 seconds + 5: +28: Time to load utils op: 0.0004782676696777344 secondsTime to load utils op: 0.00039458274841308594 secondsTime to load utils op: 0.0005037784576416016 seconds +28: +28: +28: Time to load utils op: 0.00044798851013183594 secondsTime to load utils op: 0.0004532337188720703 seconds +28: + 6: Time to load utils op: 0.20180320739746094 seconds +28: Time to load utils op: 0.00043654441833496094 seconds + 7: Time to load utils op: 0.4039299488067627 seconds + 6: Time to load utils op: 0.2022240161895752 seconds +28: Time to load utils op: 0.00037932395935058594 seconds + 7: Time to load utils op: 0.20191574096679688 seconds + 7: Time to load utils op: 0.20247364044189453 secondsTime to load utils op: 0.20250368118286133 seconds + 7: + 7: Time to load utils op: 0.20264220237731934 seconds + 7: Time to load utils op: 0.20209121704101562 seconds + 7: Time to load utils op: 0.2019801139831543 seconds + 7: Time to load utils op: 0.2022571563720703 seconds + 9: Time to load utils op: 0.4036688804626465 seconds + 9: Time to load utils op: 0.2024550437927246 seconds + 9: Time to load utils op: 0.20244956016540527 seconds + 8: Time to load utils op: 0.2032794952392578 secondsTime to load utils op: 0.2033376693725586 seconds + 8: + 9: Time to load utils op: 0.2027754783630371 seconds + 8: Time to load utils op: 0.20374727249145508 seconds + 8: Time to load utils op: 0.20361781120300293 seconds + 9: Time to load utils op: 0.20187735557556152 seconds + 9: Time to load utils op: 0.20181822776794434 seconds + 8: Time to load utils op: 0.2030472755432129 secondsTime to load utils op: 0.20305275917053223 seconds + 8: + 9: Time to load utils op: 0.20206284523010254 seconds + 9: Time to load utils op: 0.20236968994140625 seconds + 8: Time to load utils op: 0.20454096794128418 secondsTime to load utils op: 0.2045447826385498 seconds + 8: +11: Time to load utils op: 0.4035453796386719 seconds +11: Time to load utils op: 0.20183300971984863 seconds +11: Time to load utils op: 0.20173287391662598 seconds +11: Time to load utils op: 0.2026348114013672 seconds +11: Time to load utils op: 0.20203876495361328 seconds +11: Time to load utils op: 0.20195531845092773 seconds +10: Time to load utils op: 0.20422816276550293 seconds +11: Time to load utils op: 0.20179510116577148 seconds +10: Time to load utils op: 0.20314288139343262 seconds +11: Time to load utils op: 0.20201396942138672 seconds +10: Time to load utils op: 0.20371317863464355 secondsTime to load utils op: 0.20349931716918945 seconds +10: +10: Time to load utils op: 0.20370078086853027 seconds +10: Time to load utils op: 0.2038118839263916 seconds +10: Time to load utils op: 0.20518851280212402 secondsTime to load utils op: 0.20386743545532227 seconds +10: +12: Time to load utils op: 0.2040262222290039 seconds +12: Time to load utils op: 0.20348024368286133 seconds +12: Time to load utils op: 0.20391440391540527 seconds +12: Time to load utils op: 0.2039165496826172 seconds +12: Time to load utils op: 0.20331287384033203 seconds +12: Time to load utils op: 0.20394253730773926 seconds +12: Time to load utils op: 0.20327019691467285 seconds +12: Time to load utils op: 0.2045729160308838 seconds +13: Time to load utils op: 0.2033073902130127 seconds + 0: Time to load utils op: 0.0003306865692138672 seconds + 0: Time to load utils op: 0.00038886070251464844 seconds + 0: Time to load utils op: 0.0003821849822998047 seconds +16: Time to load utils op: 0.40346479415893555 seconds + 0: Time to load utils op: 0.00044536590576171875 seconds + 0: Time to load utils op: 0.0004818439483642578 seconds +14: Time to load utils op: 0.20316290855407715 seconds +13: Time to load utils op: 0.20296835899353027 seconds +14: Time to load utils op: 0.20309877395629883 seconds +14: Time to load utils op: 0.20433592796325684 secondsTime to load utils op: 0.20410394668579102 seconds +14: + 1: Time to load utils op: 0.0003495216369628906 seconds + 1: Time to load utils op: 0.0005099773406982422 seconds +14: Time to load utils op: 0.20368385314941406 seconds +15: Time to load utils op: 0.20388579368591309 seconds + 1: Time to load utils op: 0.0005154609680175781 seconds +16: Time to load utils op: 0.20220232009887695 secondsTime to load utils op: 0.20209741592407227 seconds +16: +14: Time to load utils op: 0.20383834838867188 seconds +15: Time to load utils op: 0.20377016067504883 seconds +14: Time to load utils op: 0.20461773872375488 seconds +13: Time to load utils op: 0.20225262641906738 seconds +15: Time to load utils op: 0.20275211334228516 seconds +16: Time to load utils op: 0.20183205604553223 seconds + 1: Time to load utils op: 0.0003421306610107422 seconds +15: Time to load utils op: 0.20332670211791992 seconds +16: Time to load utils op: 0.20202398300170898 seconds +15: Time to load utils op: 0.20267939567565918 secondsTime to load utils op: 0.20267820358276367 seconds +15: +13: Time to load utils op: 0.20239973068237305 seconds +15: Time to load utils op: 0.20349431037902832 seconds +13: Time to load utils op: 0.20230460166931152 seconds + 1: Time to load utils op: 0.00034689903259277344 seconds + 2: Time to load utils op: 0.0004444122314453125 seconds +16: Time to load utils op: 0.20173978805541992 seconds +13: Time to load utils op: 0.20313692092895508 seconds +13: Time to load utils op: 0.20250582695007324 seconds + 1: Time to load utils op: 0.0003578662872314453 seconds + 1: Time to load utils op: 0.0003490447998046875 seconds + 2: Time to load utils op: 0.00032258033752441406 seconds +16: Time to load utils op: 0.20215344429016113 seconds +13: Time to load utils op: 0.2024705410003662 seconds + 4: Time to load utils op: 0.00048089027404785156 seconds + 4: Time to load utils op: 0.0003571510314941406 seconds + 4: Time to load utils op: 0.0005216598510742188 seconds +16: Time to load utils op: 0.201934814453125 seconds + 1: Time to load utils op: 0.0003693103790283203 seconds + 4: Time to load utils op: 0.00034236907958984375 seconds + 2: Time to load utils op: 0.0003497600555419922 seconds + 4: Time to load utils op: 0.00034165382385253906 seconds + 3: Time to load utils op: 0.0004687309265136719 seconds + 4: Time to load utils op: 0.0003426074981689453 seconds + 2: Time to load utils op: 0.00040841102600097656 secondsTime to load utils op: 0.0004153251647949219 seconds + 2: + 2: Time to load utils op: 0.00038051605224609375 seconds + 4: Time to load utils op: 0.00033926963806152344 seconds + 4: Time to load utils op: 0.0003573894500732422 seconds + 2: Time to load utils op: 0.0003833770751953125 seconds + 3: Time to load utils op: 0.0003364086151123047 seconds + 2: Time to load utils op: 0.0003864765167236328 seconds + 3: Time to load utils op: 0.0003151893615722656 seconds + 3: Time to load utils op: 0.00039315223693847656 secondsTime to load utils op: 0.0004062652587890625 seconds + 3: + 3: Time to load utils op: 0.0003952980041503906 seconds + 3: Time to load utils op: 0.0003695487976074219 seconds +17: Time to load utils op: 0.20319700241088867 seconds + 3: Time to load utils op: 0.00036787986755371094 seconds +17: Time to load utils op: 0.20276641845703125 seconds +17: Time to load utils op: 0.203233003616333 seconds +17: Time to load utils op: 0.20360589027404785 seconds +17: Time to load utils op: 0.20402216911315918 seconds +17: Time to load utils op: 0.20388078689575195 seconds +17: Time to load utils op: 0.20277738571166992 seconds +17: Time to load utils op: 0.20325183868408203 seconds + 0: [2022-11-24 14:13:22,947] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer + 6: Time to load utils op: 0.00043773651123046875 seconds + 6: Time to load utils op: 0.0003552436828613281 seconds + 5: Time to load utils op: 0.0004069805145263672 seconds + 0: [2022-11-24 14:13:22,947] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 6: Time to load utils op: 0.000339508056640625 seconds +18: Time to load utils op: 0.20238232612609863 secondsTime to load utils op: 0.20284557342529297 seconds +18: +18: Time to load utils op: 0.203444242477417 secondsTime to load utils op: 0.20218729972839355 seconds +18: +18: Time to load utils op: 0.2030503749847412 seconds + 0: [2022-11-24 14:13:22,947] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.86 GB, percent = 6.9% + 5: Time to load utils op: 0.0003597736358642578 secondsTime to load utils op: 0.00035452842712402344 seconds + 5: +18: Time to load utils op: 0.20345115661621094 secondsTime to load utils op: 0.2026660442352295 secondsTime to load utils op: 0.20267343521118164 seconds +18: +18: +21: Time to load utils op: 0.40326952934265137 seconds + 6: Time to load utils op: 0.00035858154296875 seconds +15: Time to load utils op: 0.40294790267944336 seconds + 7: Time to load utils op: 0.0004506111145019531 seconds + 6: Time to load utils op: 0.00034546852111816406 seconds + 7: Time to load utils op: 0.00032329559326171875 seconds + 5: Time to load utils op: 0.00032019615173339844 seconds +14: Time to load utils op: 0.40328431129455566 seconds + 6: Time to load utils op: 0.0003447532653808594 seconds + 6: Time to load utils op: 0.0003657341003417969 seconds + 5: Time to load utils op: 0.0003592967987060547 seconds + 7: Time to load utils op: 0.00032806396484375 secondsTime to load utils op: 0.00031828880310058594 seconds + 7: + 5: Time to load utils op: 0.0003414154052734375 seconds + 6: Time to load utils op: 0.00035262107849121094 seconds + 7: Time to load utils op: 0.00036644935607910156 seconds + 5: Time to load utils op: 0.00034809112548828125 seconds + 5: Time to load utils op: 0.0003364086151123047 seconds + 7: Time to load utils op: 0.0003380775451660156 seconds + 7: Time to load utils op: 0.00033736228942871094 seconds + 7: Time to load utils op: 0.0003287792205810547 seconds +20: Time to load utils op: 0.202880859375 seconds +21: Time to load utils op: 0.20198392868041992 seconds +20: Time to load utils op: 0.20308184623718262 seconds +21: Time to load utils op: 0.20196104049682617 seconds +23: Time to load utils op: 0.40349650382995605 seconds +20: Time to load utils op: 0.20336079597473145 seconds + 9: Time to load utils op: 0.0005338191986083984 seconds +20: Time to load utils op: 0.20355653762817383 seconds +20: Time to load utils op: 0.20248889923095703 seconds +19: Time to load utils op: 0.20507478713989258 secondsTime to load utils op: 0.2050762176513672 secondsTime to load utils op: 0.20499634742736816 seconds +19: +19: +20: Time to load utils op: 0.2025911808013916 seconds +20: Time to load utils op: 0.20369625091552734 seconds +19: Time to load utils op: 0.2053675651550293 seconds +21: Time to load utils op: 0.20227360725402832 secondsTime to load utils op: 0.20212054252624512 seconds +21: +19: Time to load utils op: 0.20452547073364258 seconds +21: Time to load utils op: 0.20184707641601562 seconds + 9: Time to load utils op: 0.0003814697265625 seconds +19: Time to load utils op: 0.2050328254699707 seconds +21: Time to load utils op: 0.2017502784729004 seconds + 9: Time to load utils op: 0.0003292560577392578 seconds +19: Time to load utils op: 0.20510220527648926 seconds + 9: Time to load utils op: 0.0003268718719482422 seconds +20: Time to load utils op: 0.20356249809265137 seconds +19: Time to load utils op: 0.20505928993225098 seconds + 9: Time to load utils op: 0.00037670135498046875 seconds + 9: Time to load utils op: 0.0003237724304199219 seconds +21: Time to load utils op: 0.20258569717407227 seconds + 8: Time to load utils op: 0.000507354736328125 seconds + 9: Time to load utils op: 0.00033664703369140625 seconds + 9: Time to load utils op: 0.0003848075866699219 seconds + 8: Time to load utils op: 0.00035452842712402344 seconds +23: Time to load utils op: 0.20191431045532227 seconds + 8: Time to load utils op: 0.0003294944763183594 seconds +23: Time to load utils op: 0.20207667350769043 seconds + 8: Time to load utils op: 0.00039196014404296875 seconds + 8: Time to load utils op: 0.0003848075866699219 seconds + 8: Time to load utils op: 0.00035881996154785156 secondsTime to load utils op: 0.0003445148468017578 seconds + 8: + 8: Time to load utils op: 0.0003223419189453125 seconds +23: Time to load utils op: 0.2017207145690918 secondsTime to load utils op: 0.20201420783996582 seconds +23: +23: Time to load utils op: 0.20202326774597168 seconds +22: Time to load utils op: 0.2026824951171875 seconds +22: Time to load utils op: 0.20317912101745605 seconds +22: Time to load utils op: 0.20360422134399414 seconds +23: Time to load utils op: 0.20176053047180176 seconds +22: Time to load utils op: 0.20425796508789062 seconds +23: Time to load utils op: 0.20184063911437988 seconds +22: Time to load utils op: 0.2039780616760254 seconds +11: Time to load utils op: 0.0004849433898925781 seconds +11: Time to load utils op: 0.0004525184631347656 seconds +22: Time to load utils op: 0.20459532737731934 secondsTime to load utils op: 0.20454907417297363 seconds +22: +11: Time to load utils op: 0.00033354759216308594 seconds +22: Time to load utils op: 0.20352840423583984 seconds +10: Time to load utils op: 0.0003790855407714844 seconds +10: Time to load utils op: 0.0005033016204833984 seconds +11: Time to load utils op: 0.0004067420959472656 seconds +10: Time to load utils op: 0.0003504753112792969 seconds +11: Time to load utils op: 0.0003781318664550781 seconds +11: Time to load utils op: 0.0003783702850341797 seconds +11: Time to load utils op: 0.00037550926208496094 seconds +11: Time to load utils op: 0.00037360191345214844 seconds +10: Time to load utils op: 0.0003566741943359375 seconds +10: Time to load utils op: 0.00035643577575683594 seconds +10: Time to load utils op: 0.0003457069396972656 seconds +10: Time to load utils op: 0.0003910064697265625 seconds +10: Time to load utils op: 0.0003762245178222656 seconds +12: Time to load utils op: 0.0004687309265136719 seconds +12: Time to load utils op: 0.00036787986755371094 seconds +12: Time to load utils op: 0.00029587745666503906 seconds +12: Time to load utils op: 0.0003597736358642578 seconds +16: Time to load utils op: 0.0005369186401367188 seconds +12: Time to load utils op: 0.0003209114074707031 seconds +12: Time to load utils op: 0.00036144256591796875 seconds +12: Time to load utils op: 0.0003743171691894531 seconds +13: Time to load utils op: 0.0005016326904296875 seconds +12: Time to load utils op: 0.0003979206085205078 seconds +16: Time to load utils op: 0.00035762786865234375 seconds +16: Time to load utils op: 0.0003325939178466797 seconds +16: Time to load utils op: 0.0003600120544433594 seconds +16: Time to load utils op: 0.0003840923309326172 seconds +16: Time to load utils op: 0.0003731250762939453 seconds +14: Time to load utils op: 0.0003662109375 secondsTime to load utils op: 0.0004787445068359375 seconds +14: +14: Time to load utils op: 0.0004725456237792969 seconds +16: Time to load utils op: 0.0003561973571777344 seconds +15: Time to load utils op: 0.0004050731658935547 seconds +16: Time to load utils op: 0.0003669261932373047 seconds +14: Time to load utils op: 0.0003402233123779297 seconds +15: Time to load utils op: 0.00034737586975097656 seconds +14: Time to load utils op: 0.0003719329833984375 seconds +14: Time to load utils op: 0.0003247261047363281 seconds +15: Time to load utils op: 0.0003936290740966797 seconds +14: Time to load utils op: 0.0003597736358642578 seconds +15: Time to load utils op: 0.0003867149353027344 seconds +15: Time to load utils op: 0.000335693359375 seconds +15: Time to load utils op: 0.0003941059112548828 seconds +15: Time to load utils op: 0.0003561973571777344 seconds +13: Time to load utils op: 0.00038909912109375 seconds +17: Time to load utils op: 0.00045609474182128906 seconds +13: Time to load utils op: 0.0003762245178222656 seconds +13: Time to load utils op: 0.00040030479431152344 seconds +17: Time to load utils op: 0.0004024505615234375 seconds +13: Time to load utils op: 0.0004372596740722656 seconds +13: Time to load utils op: 0.0003578662872314453 seconds +17: Time to load utils op: 0.0003592967987060547 seconds +17: Time to load utils op: 0.00035190582275390625 seconds +13: Time to load utils op: 0.0003058910369873047 seconds +17: Time to load utils op: 0.0003573894500732422 seconds +17: Time to load utils op: 0.0004088878631591797 seconds +17: Time to load utils op: 0.00038909912109375 seconds +17: Time to load utils op: 0.0003883838653564453 seconds +15: Time to load utils op: 0.0003685951232910156 seconds +13: Time to load utils op: 0.0003876686096191406 seconds +21: Time to load utils op: 0.0005180835723876953 seconds +14: Time to load utils op: 0.00036978721618652344 seconds +18: Time to load utils op: 0.0005135536193847656 seconds +18: Time to load utils op: 0.0003695487976074219 seconds +18: Time to load utils op: 0.0003962516784667969 seconds +18: Time to load utils op: 0.0003662109375 seconds +18: Time to load utils op: 0.000354766845703125 seconds +18: Time to load utils op: 0.00034546852111816406 seconds +18: Time to load utils op: 0.0003314018249511719 seconds +18: Time to load utils op: 0.00031828880310058594 seconds +21: Time to load utils op: 0.00034928321838378906 seconds +21: Time to load utils op: 0.0003464221954345703 seconds +20: Time to load utils op: 0.0005407333374023438 seconds +20: Time to load utils op: 0.00038361549377441406 seconds +20: Time to load utils op: 0.0003719329833984375 seconds +21: Time to load utils op: 0.0003647804260253906 seconds +21: Time to load utils op: 0.00034809112548828125 seconds +20: Time to load utils op: 0.00031876564025878906 seconds +20: Time to load utils op: 0.00039196014404296875 seconds +21: Time to load utils op: 0.00031876564025878906 seconds +23: Time to load utils op: 0.0005085468292236328 seconds +21: Time to load utils op: 0.0003218650817871094 seconds +20: Time to load utils op: 0.0003311634063720703 seconds +20: Time to load utils op: 0.00030303001403808594 seconds +21: Time to load utils op: 0.0003211498260498047 seconds +20: Time to load utils op: 0.00036716461181640625 seconds +19: Time to load utils op: 0.00042724609375 secondsTime to load utils op: 0.000469207763671875 seconds +19: +23: Time to load utils op: 0.0003330707550048828 seconds +23: Time to load utils op: 0.0003323554992675781 seconds +19: Time to load utils op: 0.00035071372985839844 secondsTime to load utils op: 0.0003571510314941406 secondsTime to load utils op: 0.0003578662872314453 seconds +19: +19: +19: Time to load utils op: 0.0003554821014404297 seconds +19: Time to load utils op: 0.0003523826599121094 seconds +19: Time to load utils op: 0.0003437995910644531 seconds +23: Time to load utils op: 0.0004220008850097656 seconds +23: Time to load utils op: 0.0003771781921386719 seconds +23: Time to load utils op: 0.0003819465637207031 seconds +23: Time to load utils op: 0.00038051605224609375 seconds +23: Time to load utils op: 0.00037670135498046875 seconds +22: Time to load utils op: 0.0005295276641845703 seconds +22: Time to load utils op: 0.0003490447998046875 seconds +22: Time to load utils op: 0.0003104209899902344 seconds +22: Time to load utils op: 0.0003514289855957031 seconds +22: Time to load utils op: 0.0004010200500488281 seconds +22: Time to load utils op: 0.00038313865661621094 seconds +22: Time to load utils op: 0.00038552284240722656 seconds +22: Time to load utils op: 0.0003674030303955078 seconds + 0: [2022-11-24 14:13:22,990] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer + 0: [2022-11-24 14:13:22,991] [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: [2022-11-24 14:13:22,991] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.95 GB, percent = 6.9% + 0: [2022-11-24 14:13:23,023] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer + 0: [2022-11-24 14:13:23,024] [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: [2022-11-24 14:13:23,024] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 34.95 GB, percent = 6.9% + 0: [2022-11-24 14:13:23,024] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam + 0: [2022-11-24 14:13:23,024] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler + 0: [2022-11-24 14:13:23,024] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = + 0: [2022-11-24 14:13:23,024] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0002, 0.0002, 0.0002], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: + 0: [2022-11-24 14:13:23,025] [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: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] amp_enabled .................. False + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] amp_params ................... False + 0: [2022-11-24 14:13:23,025] [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: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] bfloat16_enabled ............. True + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] comms_config ................. + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] communication_data_type ...... None + 0: [2022-11-24 14:13:23,025] [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: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] curriculum_enabled ........... False + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] curriculum_params ............ False + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] dataloader_drop_last ......... False + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] disable_allgather ............ False + 0: [2022-11-24 14:13:23,025] [INFO] [config.py:1011:print] dump_state ................... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] elasticity_enabled ........... False + 0: [2022-11-24 14:13:23,026] [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: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] fp16_auto_cast ............... None + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] fp16_enabled ................. False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] global_rank .................. 0 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] load_universal_checkpoint .... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] loss_scale ................... 1.0 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] memory_breakdown ............. False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] monitor_config ............... + 0: [2022-11-24 14:13:23,026] [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: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] optimizer_name ............... None + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] optimizer_params ............. None + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] pld_enabled .................. False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] pld_params ................... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] prescale_gradients ........... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] scheduler_name ............... None + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] scheduler_params ............. None + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] sparse_attention ............. None + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] steps_per_print .............. 2000 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] train_batch_size ............. 256 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 1 + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] use_node_local_storage ....... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False + 0: [2022-11-24 14:13:23,026] [INFO] [config.py:1011:print] world_size ................... 256 + 0: [2022-11-24 14:13:23,027] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False + 0: [2022-11-24 14:13:23,027] [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: [2022-11-24 14:13:23,027] [INFO] [config.py:1011:print] zero_enabled ................. False + 0: [2022-11-24 14:13:23,027] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 + 0: [2022-11-24 14:13:23,027] [INFO] [config.py:996:print_user_config] json = { + 0: "train_micro_batch_size_per_gpu": 1, + 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: 0.0004127025604248047 seconds + 0: [2022-11-24 14:13:23,027] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=1 + 0: [2022-11-24 14:13:23,104] [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) +16: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/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_83m +16: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: will not load any checkpoints and will start from random +29: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,111] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 0: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +20: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +24: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +28: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +14: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +13: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 4: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +26: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +15: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +23: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +11: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +12: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +30: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +16: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 6: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 8: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +21: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 7: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +18: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +27: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +10: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,112] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 3: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +17: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 9: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +29: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 5: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +22: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +25: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +19: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 2: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. + 1: [2022-11-24 14:13:23,113] [WARNING] [engine.py:2581:load_checkpoint] Unable to find latest file at checkpoints_83m/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +31: time (ms) | load-checkpoint: 12.21 + 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: 2022-11-24 14:13:23 + 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 0.001673 seconds + 0: number of documents: 210604984 + 0: > dataset split: + 0: train: + 0: document indices in [0, 199864130) total of 199864130 documents + 0: validation: + 0: document indices in [199864130, 210394379) total of 10530249 documents + 0: test: + 0: document indices in [210394379, 210604984) total of 210605 documents + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.008 seconds + 0: total number of samples: 173377817 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.010 seconds + 0: total number of samples: 9118345 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.003 seconds + 0: total number of samples: 182928 + 0: total number of epochs: 1 + 0: > finished creating GPT datasets ... + 0: [after dataloaders are built] datetime: 2022-11-24 14:13:40 + 0: done with setup ... + 0: training ... + 0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +31: time (ms) | model-and-optimizer-setup: 28960.87 | train/valid/test-data-iterators-setup: 16337.19 + 0: [000-000] 0.0827B / 0.0492B + 0: [before the start of training step] datetime: 2022-11-24 14:13:40 + 0: [2022-11-24 14:13:40,718] [INFO] [checkpointing.py:553:forward] Activation Checkpointing Information + 0: [2022-11-24 14:13:40,718] [INFO] [checkpointing.py:554:forward] ----Partition Activations False, CPU CHECKPOINTING False + 0: [2022-11-24 14:13:40,718] [INFO] [checkpointing.py:557:forward] ----contiguous Memory Checkpointing False with None total layers + 0: [2022-11-24 14:13:40,718] [INFO] [checkpointing.py:560:forward] ----Synchronization False + 0: [2022-11-24 14:13:40,718] [INFO] [checkpointing.py:561:forward] ----Profiling time in checkpointing False + 0: [Rank 0] (after 10 iterations) memory (MB) | allocated: 1043.29638671875 | max allocated: 1703.8681640625 | reserved: 2544.0 | max reserved: 2544.0 +31: iteration 10/ 37905 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 1.10 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 9.341081E+00 | grad norm: 1.581 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 232.943 | TFLOPs: 1.48 | +31: iteration 20/ 37905 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 0.22 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 8.007067E+00 | grad norm: 1.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.579 | TFLOPs: 7.53 | +31: iteration 30/ 37905 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 0.22 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 7.355876E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.068 | TFLOPs: 7.53 | +31: iteration 40/ 37905 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 0.22 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 7.092228E+00 | grad norm: 1.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.268 | TFLOPs: 7.47 | +31: iteration 50/ 37905 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.924334E+00 | grad norm: 0.979 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.628 | TFLOPs: 6.93 | +31: iteration 60/ 37905 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.817952E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.772 | TFLOPs: 6.88 | +31: iteration 70/ 37905 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.654077E+00 | grad norm: 0.655 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.865 | TFLOPs: 6.53 | +31: iteration 80/ 37905 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 0.28 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.505041E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 899.786 | TFLOPs: 5.73 | +31: iteration 90/ 37905 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.424773E+00 | grad norm: 0.765 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.828 | TFLOPs: 6.75 | +31: iteration 100/ 37905 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.303482E+00 | grad norm: 0.494 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.659 | TFLOPs: 6.95 | +31: iteration 110/ 37905 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 0.22 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.198562E+00 | grad norm: 0.822 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.209 | TFLOPs: 7.25 | +31: iteration 120/ 37905 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 0.28 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 6.093964E+00 | grad norm: 0.788 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 907.201 | TFLOPs: 5.78 | +31: iteration 130/ 37905 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.977559E+00 | grad norm: 0.640 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.597 | TFLOPs: 6.63 | +31: iteration 140/ 37905 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 0.26 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.905592E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 999.168 | TFLOPs: 6.36 | +31: iteration 150/ 37905 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 0.26 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.857211E+00 | grad norm: 0.540 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 985.395 | TFLOPs: 6.28 | +31: iteration 160/ 37905 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 0.31 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.744721E+00 | grad norm: 0.434 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.014 | TFLOPs: 5.27 | +31: iteration 170/ 37905 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.734492E+00 | grad norm: 0.723 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.525 | TFLOPs: 6.42 | +31: iteration 180/ 37905 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 0.27 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.643021E+00 | grad norm: 0.602 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 950.146 | TFLOPs: 6.05 | +31: iteration 190/ 37905 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 0.28 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.618031E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 930.569 | TFLOPs: 5.93 | +31: iteration 200/ 37905 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 0.28 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.560971E+00 | grad norm: 0.488 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 909.385 | TFLOPs: 5.79 | +31: iteration 210/ 37905 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 0.21 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.535940E+00 | grad norm: 0.729 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.463 | TFLOPs: 7.72 | +31: iteration 220/ 37905 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.475412E+00 | grad norm: 0.592 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.540 | TFLOPs: 8.51 | +31: iteration 230/ 37905 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 0.20 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.453100E+00 | grad norm: 0.543 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.293 | TFLOPs: 8.05 | +31: iteration 240/ 37905 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.441629E+00 | grad norm: 0.816 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.576 | TFLOPs: 7.19 | +31: iteration 250/ 37905 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 0.26 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.382257E+00 | grad norm: 0.670 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 971.796 | TFLOPs: 6.19 | +31: iteration 260/ 37905 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.379037E+00 | grad norm: 0.594 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1380.682 | TFLOPs: 8.79 | +31: iteration 270/ 37905 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.300028E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1332.585 | TFLOPs: 8.49 | +31: iteration 280/ 37905 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.285769E+00 | grad norm: 0.742 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1379.682 | TFLOPs: 8.79 | +31: iteration 290/ 37905 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.237854E+00 | grad norm: 0.742 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1329.044 | TFLOPs: 8.46 | +31: iteration 300/ 37905 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 0.20 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.178745E+00 | grad norm: 0.589 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1287.820 | TFLOPs: 8.20 | +31: iteration 310/ 37905 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.202284E+00 | grad norm: 0.478 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.947 | TFLOPs: 8.44 | +31: iteration 320/ 37905 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 0.20 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.184935E+00 | grad norm: 0.557 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.939 | TFLOPs: 7.99 | +31: iteration 330/ 37905 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 0.20 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.156120E+00 | grad norm: 0.682 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.255 | TFLOPs: 8.19 | +31: iteration 340/ 37905 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.127128E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.375 | TFLOPs: 8.52 | +31: iteration 350/ 37905 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 0.20 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.078787E+00 | grad norm: 0.555 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.208 | TFLOPs: 8.26 | +31: iteration 360/ 37905 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.043867E+00 | grad norm: 0.572 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.749 | TFLOPs: 8.48 | +31: iteration 370/ 37905 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 0.20 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.006816E+00 | grad norm: 1.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.306 | TFLOPs: 8.31 | +31: iteration 380/ 37905 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 0.23 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 5.013401E+00 | grad norm: 0.519 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1136.421 | TFLOPs: 7.24 | +31: iteration 390/ 37905 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 0.22 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.963657E+00 | grad norm: 0.654 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.720 | TFLOPs: 7.28 | +31: iteration 400/ 37905 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 0.19 | learning rate: 2.000E-04 | global batch size: 256 | lm loss: 4.976614E+00 | grad norm: 0.824 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.303 | TFLOPs: 8.45 | +31: iteration 410/ 37905 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 0.19 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.946059E+00 | grad norm: 0.495 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.602 | TFLOPs: 8.37 | +31: iteration 420/ 37905 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.975524E+00 | grad norm: 0.654 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.156 | TFLOPs: 7.99 | +31: iteration 430/ 37905 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.912059E+00 | grad norm: 0.732 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.600 | TFLOPs: 8.31 | +31: iteration 440/ 37905 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 0.19 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.875040E+00 | grad norm: 0.614 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.686 | TFLOPs: 8.45 | +31: iteration 450/ 37905 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 0.19 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.838276E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.048 | TFLOPs: 8.45 | +31: iteration 460/ 37905 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.852543E+00 | grad norm: 0.882 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1390.367 | TFLOPs: 8.85 | +31: iteration 470/ 37905 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 0.22 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.841634E+00 | grad norm: 0.822 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.639 | TFLOPs: 7.35 | +31: iteration 480/ 37905 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 0.22 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.824133E+00 | grad norm: 0.565 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.983 | TFLOPs: 7.43 | +31: iteration 490/ 37905 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 0.22 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.766006E+00 | grad norm: 0.558 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.687 | TFLOPs: 7.38 | +31: iteration 500/ 37905 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 0.19 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.754567E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.113 | TFLOPs: 8.52 | +31: iteration 510/ 37905 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.736829E+00 | grad norm: 0.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1410.721 | TFLOPs: 8.98 | +31: iteration 520/ 37905 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.721606E+00 | grad norm: 0.704 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1411.836 | TFLOPs: 8.99 | +31: iteration 530/ 37905 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.668261E+00 | grad norm: 0.876 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.074 | TFLOPs: 8.35 | +31: iteration 540/ 37905 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.725656E+00 | grad norm: 0.668 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.521 | TFLOPs: 8.36 | +31: iteration 550/ 37905 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 0.21 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.704484E+00 | grad norm: 0.526 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.233 | TFLOPs: 7.62 | +31: iteration 560/ 37905 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.711111E+00 | grad norm: 0.893 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.573 | TFLOPs: 8.18 | +31: iteration 570/ 37905 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.661661E+00 | grad norm: 0.729 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1257.687 | TFLOPs: 8.01 | +31: iteration 580/ 37905 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.619470E+00 | grad norm: 0.676 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1445.749 | TFLOPs: 9.21 | +31: iteration 590/ 37905 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.575243E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1425.688 | TFLOPs: 9.08 | +31: iteration 600/ 37905 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.567682E+00 | grad norm: 0.741 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.354 | TFLOPs: 8.21 | +31: iteration 610/ 37905 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.571619E+00 | grad norm: 0.659 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.208 | TFLOPs: 8.11 | +31: iteration 620/ 37905 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 0.21 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.524535E+00 | grad norm: 0.674 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.871 | TFLOPs: 7.76 | +31: iteration 630/ 37905 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.593814E+00 | grad norm: 0.628 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.285 | TFLOPs: 7.98 | +31: iteration 640/ 37905 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.514336E+00 | grad norm: 0.740 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1413.580 | TFLOPs: 9.00 | +31: iteration 650/ 37905 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.539438E+00 | grad norm: 0.586 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.807 | TFLOPs: 8.11 | +31: iteration 660/ 37905 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.482303E+00 | grad norm: 0.694 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1424.293 | TFLOPs: 9.07 | +31: iteration 670/ 37905 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 0.18 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.434084E+00 | grad norm: 0.536 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1389.272 | TFLOPs: 8.85 | +31: iteration 680/ 37905 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.443948E+00 | grad norm: 0.674 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.492 | TFLOPs: 8.11 | +31: iteration 690/ 37905 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 0.20 | learning rate: 1.999E-04 | global batch size: 256 | lm loss: 4.435867E+00 | grad norm: 0.919 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.250 | TFLOPs: 8.16 | +31: iteration 700/ 37905 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.420060E+00 | grad norm: 0.992 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.185 | TFLOPs: 8.97 | +31: iteration 710/ 37905 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.419109E+00 | grad norm: 0.710 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1421.745 | TFLOPs: 9.05 | +31: iteration 720/ 37905 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.435260E+00 | grad norm: 0.885 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1427.828 | TFLOPs: 9.09 | +31: iteration 730/ 37905 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 0.20 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.395219E+00 | grad norm: 0.799 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1306.120 | TFLOPs: 8.32 | +31: iteration 740/ 37905 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 0.19 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.359615E+00 | grad norm: 0.905 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.219 | TFLOPs: 8.58 | +31: iteration 750/ 37905 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 0.19 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.301876E+00 | grad norm: 0.741 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1357.914 | TFLOPs: 8.65 | +31: iteration 760/ 37905 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.335264E+00 | grad norm: 0.872 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1413.743 | TFLOPs: 9.00 | +31: iteration 770/ 37905 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.337473E+00 | grad norm: 0.776 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1415.767 | TFLOPs: 9.02 | +31: iteration 780/ 37905 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.261087E+00 | grad norm: 0.702 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1428.821 | TFLOPs: 9.10 | +31: iteration 790/ 37905 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 0.20 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.226977E+00 | grad norm: 0.752 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.109 | TFLOPs: 8.24 | +31: iteration 800/ 37905 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 0.19 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.203490E+00 | grad norm: 0.771 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1374.670 | TFLOPs: 8.75 | +31: iteration 810/ 37905 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 0.20 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.162145E+00 | grad norm: 0.779 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.469 | TFLOPs: 8.01 | +31: iteration 820/ 37905 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 0.19 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.173354E+00 | grad norm: 0.877 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.621 | TFLOPs: 8.55 | +31: iteration 830/ 37905 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 0.19 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.185663E+00 | grad norm: 0.771 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1355.755 | TFLOPs: 8.63 | +31: iteration 840/ 37905 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 0.22 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.108308E+00 | grad norm: 0.825 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.131 | TFLOPs: 7.45 | +31: iteration 850/ 37905 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.097799E+00 | grad norm: 1.047 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1439.200 | TFLOPs: 9.17 | +31: iteration 860/ 37905 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 0.19 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.081672E+00 | grad norm: 1.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.994 | TFLOPs: 8.58 | +31: iteration 870/ 37905 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 0.21 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.100893E+00 | grad norm: 0.628 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.890 | TFLOPs: 7.92 | +31: iteration 880/ 37905 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 0.18 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.087362E+00 | grad norm: 0.793 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1414.256 | TFLOPs: 9.01 | +31: iteration 890/ 37905 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 0.20 | learning rate: 1.998E-04 | global batch size: 256 | lm loss: 4.032580E+00 | grad norm: 0.701 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.164 | TFLOPs: 8.03 | +31: iteration 900/ 37905 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 0.20 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.009752E+00 | grad norm: 0.728 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1262.027 | TFLOPs: 8.04 | +31: iteration 910/ 37905 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 0.20 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.029176E+00 | grad norm: 0.674 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.514 | TFLOPs: 8.05 | +31: iteration 920/ 37905 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 0.20 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 4.032428E+00 | grad norm: 1.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1306.616 | TFLOPs: 8.32 | +31: iteration 930/ 37905 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 0.18 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.966711E+00 | grad norm: 0.683 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1414.236 | TFLOPs: 9.01 | +31: iteration 940/ 37905 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 0.17 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.950689E+00 | grad norm: 0.641 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1481.720 | TFLOPs: 9.44 | +31: iteration 950/ 37905 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 0.20 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.971202E+00 | grad norm: 0.653 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.886 | TFLOPs: 8.24 | +31: iteration 960/ 37905 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 0.19 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.945173E+00 | grad norm: 0.980 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1370.936 | TFLOPs: 8.73 | +31: iteration 970/ 37905 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 0.19 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.938909E+00 | grad norm: 0.808 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1371.879 | TFLOPs: 8.74 | +31: iteration 980/ 37905 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 0.19 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.895487E+00 | grad norm: 0.885 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.113 | TFLOPs: 8.69 | +31: iteration 990/ 37905 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 0.20 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.917822E+00 | grad norm: 0.615 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.361 | TFLOPs: 8.12 | +31: iteration 1000/ 37905 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 0.21 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.882757E+00 | grad norm: 0.704 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.876 | TFLOPs: 7.85 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 1000 | lm loss value: 3.775590E+00 | lm loss PPL: 4.362323E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 1000 to checkpoints_83m + 0: [2022-11-24 14:17:16,542] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! + 0: [2022-11-24 14:17:16,552] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,626] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,651] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,662] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,695] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,706] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,717] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,739] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:17:16,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:17:16,741] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step1000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:17:16,741] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:17:16,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:17:16,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step1000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:17:16,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:17:16,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +15: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +13: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +20: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +12: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 2: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +11: [2022-11-24 14:17:16,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:17:16,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +10: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +16: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 6: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 6: [2022-11-24 14:17:16,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 4: [2022-11-24 14:17:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +27: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +15: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +12: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +12: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +13: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +20: [2022-11-24 14:17:16,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:17:16,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 2: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:17:16,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +11: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +10: [2022-11-24 14:17:16,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +25: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +24: [2022-11-24 14:17:16,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:17:16,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 6: [2022-11-24 14:17:16,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:17:16,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 4: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:17:16,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +27: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:17:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:17:16,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +15: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +15: [2022-11-24 14:17:16,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +12: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:17:16,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +13: [2022-11-24 14:17:16,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +13: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 2: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:17:16,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:17:16,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +10: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +25: [2022-11-24 14:17:16,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +29: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 4: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +16: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 14:17:16,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:17:16,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +27: [2022-11-24 14:17:16,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +27: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:17:16,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:17:16,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +12: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +15: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:17:16,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +13: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:17:16,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:17:16,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 2: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +10: [2022-11-24 14:17:16,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +25: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:17:16,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 6: [2022-11-24 14:17:16,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +16: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:17:16,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 4: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:17:16,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +29: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:17:16,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +27: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:17:16,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +15: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +12: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +12: [2022-11-24 14:17:16,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +12: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +13: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 2: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:17:16,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:17:16,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +10: [2022-11-24 14:17:16,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +25: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +24: [2022-11-24 14:17:16,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:17:16,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 6: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +16: [2022-11-24 14:17:16,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 4: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:17:16,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:17:16,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +27: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:17:16,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +12: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +15: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:17:16,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +13: [2022-11-24 14:17:16,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:17:16,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 2: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:17:16,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +11: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +24: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +25: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +25: [2022-11-24 14:17:16,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 6: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +16: [2022-11-24 14:17:16,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:17:16,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:17:16,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +17: [2022-11-24 14:17:16,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 4: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +27: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:17:16,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:17:16,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:17:16,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +30: [2022-11-24 14:17:16,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:17:16,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +12: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +15: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +20: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +20: [2022-11-24 14:17:16,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +13: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 2: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:17:16,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:17:16,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:17:16,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +24: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +24: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +10: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +25: [2022-11-24 14:17:16,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:17:16,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 6: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +16: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 14:17:16,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +17: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +14: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 4: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +15: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +23: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +18: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +11: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +29: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +14: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +24: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +21: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +23: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +18: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +17: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +29: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +25: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +19: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +22: [2022-11-24 14:17:16,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 3: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +13: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +26: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +15: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +24: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +21: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +11: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 9: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +31: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +10: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +19: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +22: [2022-11-24 14:17:16,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 1: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 8: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +13: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +26: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +31: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +28: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +10: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 7: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step1000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +28: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +30: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 5: [2022-11-24 14:17:16,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! + 0: successfully saved checkpoint at iteration 1000 to checkpoints_83m +31: time (ms) | save-checkpoint: 326.97 +31: iteration 1010/ 37905 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 0.25 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.912927E+00 | grad norm: 0.689 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1024.706 | TFLOPs: 6.53 | +31: iteration 1020/ 37905 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 0.18 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.876365E+00 | grad norm: 0.591 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1386.459 | TFLOPs: 8.83 | +31: iteration 1030/ 37905 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 0.22 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.860173E+00 | grad norm: 0.785 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.483 | TFLOPs: 7.50 | +31: iteration 1040/ 37905 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 0.19 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.909396E+00 | grad norm: 0.775 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1337.604 | TFLOPs: 8.52 | +31: iteration 1050/ 37905 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 0.18 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.878069E+00 | grad norm: 0.632 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1397.234 | TFLOPs: 8.90 | +31: iteration 1060/ 37905 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 0.18 | learning rate: 1.997E-04 | global batch size: 256 | lm loss: 3.841062E+00 | grad norm: 0.786 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1436.361 | TFLOPs: 9.15 | +31: iteration 1070/ 37905 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 0.20 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.835279E+00 | grad norm: 0.625 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.752 | TFLOPs: 7.96 | +31: iteration 1080/ 37905 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 0.20 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.773260E+00 | grad norm: 0.607 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.404 | TFLOPs: 8.12 | +31: iteration 1090/ 37905 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 0.18 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.807774E+00 | grad norm: 0.805 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1388.587 | TFLOPs: 8.84 | +31: iteration 1100/ 37905 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 0.19 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.835730E+00 | grad norm: 0.788 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1360.926 | TFLOPs: 8.67 | +31: iteration 1110/ 37905 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 0.20 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.796785E+00 | grad norm: 0.999 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1301.206 | TFLOPs: 8.29 | +31: iteration 1120/ 37905 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 0.20 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.831940E+00 | grad norm: 0.592 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1285.048 | TFLOPs: 8.18 | +31: iteration 1130/ 37905 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 0.18 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.822455E+00 | grad norm: 0.709 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1421.330 | TFLOPs: 9.05 | +31: iteration 1140/ 37905 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 0.19 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.770451E+00 | grad norm: 0.587 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.173 | TFLOPs: 8.52 | +31: iteration 1150/ 37905 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 0.19 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.808890E+00 | grad norm: 0.811 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1356.501 | TFLOPs: 8.64 | +31: iteration 1160/ 37905 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 0.20 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.796638E+00 | grad norm: 0.734 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1299.418 | TFLOPs: 8.28 | +31: iteration 1170/ 37905 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 0.21 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.793428E+00 | grad norm: 0.681 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1198.938 | TFLOPs: 7.64 | +31: iteration 1180/ 37905 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 0.20 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.805441E+00 | grad norm: 0.605 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.711 | TFLOPs: 8.12 | +31: iteration 1190/ 37905 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 0.23 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.806501E+00 | grad norm: 0.564 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.832 | TFLOPs: 6.99 | +31: iteration 1200/ 37905 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 0.17 | learning rate: 1.996E-04 | global batch size: 256 | lm loss: 3.771244E+00 | grad norm: 0.538 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1478.979 | TFLOPs: 9.42 | +31: iteration 1210/ 37905 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.759696E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.445 | TFLOPs: 7.18 | +31: iteration 1220/ 37905 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 0.20 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.703153E+00 | grad norm: 0.762 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.027 | TFLOPs: 8.31 | +31: iteration 1230/ 37905 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 0.20 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.760323E+00 | grad norm: 0.673 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1300.001 | TFLOPs: 8.28 | +31: iteration 1240/ 37905 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 0.24 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.731477E+00 | grad norm: 0.723 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.941 | TFLOPs: 6.76 | +31: iteration 1250/ 37905 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 0.22 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.731733E+00 | grad norm: 0.630 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.433 | TFLOPs: 7.32 | +31: iteration 1260/ 37905 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 0.20 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.667848E+00 | grad norm: 0.613 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.374 | TFLOPs: 8.14 | +31: iteration 1270/ 37905 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 0.22 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.736602E+00 | grad norm: 0.582 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.740 | TFLOPs: 7.55 | +31: iteration 1280/ 37905 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 0.23 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.740067E+00 | grad norm: 0.662 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.352 | TFLOPs: 7.23 | +31: iteration 1290/ 37905 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 0.19 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.612774E+00 | grad norm: 0.578 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.663 | TFLOPs: 8.49 | +31: iteration 1300/ 37905 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 0.21 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.697206E+00 | grad norm: 0.720 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.490 | TFLOPs: 7.61 | +31: iteration 1310/ 37905 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 0.21 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.680502E+00 | grad norm: 0.672 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1228.507 | TFLOPs: 7.82 | +31: iteration 1320/ 37905 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 0.21 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.678572E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.242 | TFLOPs: 7.75 | +31: iteration 1330/ 37905 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 0.20 | learning rate: 1.995E-04 | global batch size: 256 | lm loss: 3.681024E+00 | grad norm: 0.544 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.356 | TFLOPs: 8.24 | +31: iteration 1340/ 37905 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 0.20 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.695061E+00 | grad norm: 0.553 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.123 | TFLOPs: 8.15 | +31: iteration 1350/ 37905 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 0.20 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.676358E+00 | grad norm: 0.688 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.481 | TFLOPs: 8.06 | +31: iteration 1360/ 37905 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 0.21 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.631698E+00 | grad norm: 0.635 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.424 | TFLOPs: 7.88 | +31: iteration 1370/ 37905 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 0.21 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.667451E+00 | grad norm: 0.566 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.985 | TFLOPs: 7.85 | +31: iteration 1380/ 37905 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 0.22 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.667004E+00 | grad norm: 0.615 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.139 | TFLOPs: 7.41 | +31: iteration 1390/ 37905 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 0.19 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.672223E+00 | grad norm: 0.602 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.036 | TFLOPs: 8.55 | +31: iteration 1400/ 37905 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 0.20 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.709090E+00 | grad norm: 0.675 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.050 | TFLOPs: 8.22 | +31: iteration 1410/ 37905 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 0.20 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.664329E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.381 | TFLOPs: 8.17 | +31: iteration 1420/ 37905 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 0.22 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.613468E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.822 | TFLOPs: 7.38 | +31: iteration 1430/ 37905 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 0.21 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.622853E+00 | grad norm: 0.624 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.851 | TFLOPs: 7.73 | +31: iteration 1440/ 37905 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 0.21 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.651233E+00 | grad norm: 0.635 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.814 | TFLOPs: 7.81 | +31: iteration 1450/ 37905 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 0.23 | learning rate: 1.994E-04 | global batch size: 256 | lm loss: 3.645125E+00 | grad norm: 0.669 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.443 | TFLOPs: 7.03 | +31: iteration 1460/ 37905 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.657611E+00 | grad norm: 0.626 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.573 | TFLOPs: 7.12 | +31: iteration 1470/ 37905 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 0.21 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.620548E+00 | grad norm: 0.608 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.929 | TFLOPs: 7.90 | +31: iteration 1480/ 37905 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.645491E+00 | grad norm: 0.522 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.243 | TFLOPs: 7.20 | +31: iteration 1490/ 37905 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 0.24 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.659496E+00 | grad norm: 0.654 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.666 | TFLOPs: 6.84 | +31: iteration 1500/ 37905 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 0.22 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.643785E+00 | grad norm: 0.667 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.875 | TFLOPs: 7.26 | +31: iteration 1510/ 37905 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 0.19 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.638478E+00 | grad norm: 0.780 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.421 | TFLOPs: 8.55 | +31: iteration 1520/ 37905 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 0.20 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.633441E+00 | grad norm: 0.561 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.643 | TFLOPs: 8.06 | +31: iteration 1530/ 37905 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 0.23 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.615474E+00 | grad norm: 0.537 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.725 | TFLOPs: 7.12 | +31: iteration 1540/ 37905 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 0.21 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.631085E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.775 | TFLOPs: 7.87 | +31: iteration 1550/ 37905 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 0.20 | learning rate: 1.993E-04 | global batch size: 256 | lm loss: 3.597696E+00 | grad norm: 0.467 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.743 | TFLOPs: 8.11 | +31: iteration 1560/ 37905 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 0.19 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.580010E+00 | grad norm: 0.911 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1331.056 | TFLOPs: 8.48 | +31: iteration 1570/ 37905 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 0.21 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.582675E+00 | grad norm: 0.561 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.982 | TFLOPs: 7.68 | +31: iteration 1580/ 37905 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 0.20 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.611008E+00 | grad norm: 0.659 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.927 | TFLOPs: 8.08 | +31: iteration 1590/ 37905 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 0.19 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.616109E+00 | grad norm: 0.611 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.633 | TFLOPs: 8.51 | +31: iteration 1600/ 37905 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 0.22 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.586841E+00 | grad norm: 0.530 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.418 | TFLOPs: 7.42 | +31: iteration 1610/ 37905 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 0.21 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.564185E+00 | grad norm: 0.503 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.334 | TFLOPs: 7.75 | +31: iteration 1620/ 37905 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 0.19 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.566058E+00 | grad norm: 0.621 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1379.723 | TFLOPs: 8.79 | +31: iteration 1630/ 37905 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 0.19 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.587155E+00 | grad norm: 0.620 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1344.059 | TFLOPs: 8.56 | +31: iteration 1640/ 37905 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 0.20 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.555934E+00 | grad norm: 0.684 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1302.263 | TFLOPs: 8.29 | +31: iteration 1650/ 37905 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 0.20 | learning rate: 1.992E-04 | global batch size: 256 | lm loss: 3.629882E+00 | grad norm: 0.773 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.207 | TFLOPs: 8.11 | +31: iteration 1660/ 37905 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 0.19 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.548745E+00 | grad norm: 0.696 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.700 | TFLOPs: 8.58 | +31: iteration 1670/ 37905 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 0.18 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.581975E+00 | grad norm: 0.620 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1389.351 | TFLOPs: 8.85 | +31: iteration 1680/ 37905 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 0.21 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.552959E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.310 | TFLOPs: 7.65 | +31: iteration 1690/ 37905 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 0.20 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.604395E+00 | grad norm: 0.485 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.365 | TFLOPs: 7.98 | +31: iteration 1700/ 37905 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 0.19 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.597589E+00 | grad norm: 0.590 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1379.682 | TFLOPs: 8.79 | +31: iteration 1710/ 37905 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 0.19 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.561801E+00 | grad norm: 0.706 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1331.423 | TFLOPs: 8.48 | +31: iteration 1720/ 37905 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 0.19 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.562131E+00 | grad norm: 0.587 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.814 | TFLOPs: 8.57 | +31: iteration 1730/ 37905 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 0.23 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.551853E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.102 | TFLOPs: 7.04 | +31: iteration 1740/ 37905 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 0.20 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.591692E+00 | grad norm: 0.704 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.207 | TFLOPs: 8.31 | +31: iteration 1750/ 37905 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 0.20 | learning rate: 1.991E-04 | global batch size: 256 | lm loss: 3.561883E+00 | grad norm: 0.571 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.122 | TFLOPs: 8.07 | +31: iteration 1760/ 37905 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 0.20 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.574907E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.050 | TFLOPs: 8.10 | +31: iteration 1770/ 37905 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 0.21 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.535203E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.996 | TFLOPs: 7.92 | +31: iteration 1780/ 37905 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 0.22 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.527107E+00 | grad norm: 0.584 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.658 | TFLOPs: 7.30 | +31: iteration 1790/ 37905 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 0.19 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.582730E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.504 | TFLOPs: 8.44 | +31: iteration 1800/ 37905 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 0.22 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.523845E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.200 | TFLOPs: 7.27 | +31: iteration 1810/ 37905 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 0.22 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.558498E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.918 | TFLOPs: 7.43 | +31: iteration 1820/ 37905 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 0.20 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.535329E+00 | grad norm: 0.643 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1291.104 | TFLOPs: 8.22 | +31: iteration 1830/ 37905 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 0.20 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.524284E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.274 | TFLOPs: 8.25 | +31: iteration 1840/ 37905 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 0.19 | learning rate: 1.990E-04 | global batch size: 256 | lm loss: 3.527487E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.452 | TFLOPs: 8.46 | +31: iteration 1850/ 37905 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 0.19 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.538001E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.374 | TFLOPs: 8.43 | +31: iteration 1860/ 37905 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 0.18 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.492926E+00 | grad norm: 0.518 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1400.046 | TFLOPs: 8.92 | +31: iteration 1870/ 37905 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 0.18 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.504316E+00 | grad norm: 0.499 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1385.562 | TFLOPs: 8.82 | +31: iteration 1880/ 37905 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 0.19 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.490803E+00 | grad norm: 0.537 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1334.459 | TFLOPs: 8.50 | +31: iteration 1890/ 37905 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 0.19 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.543024E+00 | grad norm: 0.467 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.395 | TFLOPs: 8.42 | +31: iteration 1900/ 37905 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 0.22 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.474939E+00 | grad norm: 0.492 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.039 | TFLOPs: 7.32 | +31: iteration 1910/ 37905 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 0.23 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.537589E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.224 | TFLOPs: 7.06 | +31: iteration 1920/ 37905 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 0.20 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.494212E+00 | grad norm: 0.472 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.774 | TFLOPs: 8.20 | +31: iteration 1930/ 37905 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 0.19 | learning rate: 1.989E-04 | global batch size: 256 | lm loss: 3.508223E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.068 | TFLOPs: 8.78 | +31: iteration 1940/ 37905 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.498187E+00 | grad norm: 0.507 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.440 | TFLOPs: 7.18 | +31: iteration 1950/ 37905 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.480487E+00 | grad norm: 0.641 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.543 | TFLOPs: 7.20 | +31: iteration 1960/ 37905 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 0.22 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.545077E+00 | grad norm: 0.445 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.937 | TFLOPs: 7.50 | +31: iteration 1970/ 37905 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 0.22 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.547785E+00 | grad norm: 0.658 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.853 | TFLOPs: 7.50 | +31: iteration 1980/ 37905 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 0.22 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.513939E+00 | grad norm: 0.603 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.068 | TFLOPs: 7.40 | +31: iteration 1990/ 37905 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 0.20 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.543996E+00 | grad norm: 0.597 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.176 | TFLOPs: 8.21 | + 0: [2022-11-24 14:20:41,319] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00019876637624003125, 0.00019876637624003125, 0.00019876637624003125], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 2000/ 37905 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 0.19 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.534968E+00 | grad norm: 0.503 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1363.077 | TFLOPs: 8.68 | + 0: steps: 2000 loss: 3.6141 iter time (s): 0.208 samples/sec: 1228.109 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 2000 | lm loss value: 3.368681E+00 | lm loss PPL: 2.904021E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 2000 to checkpoints_83m + 0: [2022-11-24 14:20:41,404] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! + 0: [2022-11-24 14:20:41,412] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,497] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,519] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,530] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,542] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,575] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,598] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:20:41,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:20:41,599] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step2000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:20:41,599] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:20:41,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:20:41,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step2000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +18: [2022-11-24 14:20:41,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 14:20:41,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:20:41,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:20:41,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 5: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +19: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +28: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 8: [2022-11-24 14:20:41,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:20:41,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 3: [2022-11-24 14:20:41,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,676] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +18: [2022-11-24 14:20:41,676] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:20:41,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,677] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:20:41,677] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +21: [2022-11-24 14:20:41,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +26: [2022-11-24 14:20:41,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +30: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +26: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:20:41,678] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:20:41,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:20:41,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:20:41,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +14: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,679] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,679] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 2: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:20:41,680] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 8: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +28: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:20:41,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:20:41,681] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,681] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +19: [2022-11-24 14:20:41,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,682] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,682] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 3: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +18: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +20: [2022-11-24 14:20:41,683] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +22: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:20:41,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +26: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +30: [2022-11-24 14:20:41,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:20:41,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,684] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:20:41,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:20:41,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,685] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:20:41,685] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:20:41,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:20:41,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 2: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,686] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +29: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,686] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 8: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +28: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,687] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 5: [2022-11-24 14:20:41,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:20:41,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +19: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:20:41,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:20:41,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,688] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,688] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:20:41,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 3: [2022-11-24 14:20:41,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +18: [2022-11-24 14:20:41,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,689] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:20:41,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +26: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:20:41,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +30: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +30: [2022-11-24 14:20:41,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:20:41,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:20:41,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:20:41,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:20:41,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:20:41,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +15: [2022-11-24 14:20:41,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:20:41,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:20:41,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 2: [2022-11-24 14:20:41,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:20:41,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +29: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +28: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 5: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +19: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +14: [2022-11-24 14:20:41,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +18: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 3: [2022-11-24 14:20:41,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:20:41,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +30: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:20:41,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:20:41,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:20:41,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:20:41,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:20:41,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:20:41,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:20:41,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:20:41,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 2: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:20:41,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:20:41,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 8: [2022-11-24 14:20:41,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +28: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:20:41,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 5: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:20:41,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +14: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +19: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:20:41,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 3: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +26: [2022-11-24 14:20:41,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +26: [2022-11-24 14:20:41,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:20:41,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:20:41,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:20:41,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:20:41,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:20:41,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:20:41,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +15: [2022-11-24 14:20:41,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +16: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 2: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:20:41,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 8: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:20:41,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +28: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 5: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:20:41,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:20:41,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +14: [2022-11-24 14:20:41,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +19: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:20:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 3: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:20:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 3: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +20: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 14:20:41,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +26: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 7: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:20:41,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +21: [2022-11-24 14:20:41,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +30: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:20:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:20:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:20:41,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:20:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 2: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:20:41,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:20:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 9: [2022-11-24 14:20:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:20:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:20:41,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 5: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +28: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +27: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +14: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +19: [2022-11-24 14:20:41,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 6: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +30: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +30: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +26: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +26: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +15: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +24: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +21: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +18: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +12: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +27: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +14: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +15: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +24: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +21: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +23: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +18: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +12: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +29: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +10: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +14: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 8: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +26: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +10: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +13: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +11: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +22: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +26: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +17: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +31: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +25: [2022-11-24 14:20:41,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +19: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +22: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +14: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +17: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +31: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +25: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +13: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 4: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +11: [2022-11-24 14:20:41,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +16: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 1: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:20:41,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step2000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:20:41,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! + 0: successfully saved checkpoint at iteration 2000 to checkpoints_83m +31: time (ms) | save-checkpoint: 318.71 +31: iteration 2010/ 37905 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 0.23 | learning rate: 1.988E-04 | global batch size: 256 | lm loss: 3.550495E+00 | grad norm: 0.578 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.802 | TFLOPs: 7.18 | +31: iteration 2020/ 37905 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 0.22 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.561443E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.892 | TFLOPs: 7.58 | +31: iteration 2030/ 37905 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 0.19 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.472791E+00 | grad norm: 0.633 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1339.552 | TFLOPs: 8.53 | +31: iteration 2040/ 37905 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 0.21 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.497687E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.794 | TFLOPs: 7.61 | +31: iteration 2050/ 37905 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 0.20 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.528379E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.080 | TFLOPs: 7.96 | +31: iteration 2060/ 37905 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 0.21 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.498368E+00 | grad norm: 0.440 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.975 | TFLOPs: 7.89 | +31: iteration 2070/ 37905 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 0.22 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.476973E+00 | grad norm: 0.465 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.204 | TFLOPs: 7.39 | +31: iteration 2080/ 37905 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 0.20 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.497636E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.497 | TFLOPs: 8.33 | +31: iteration 2090/ 37905 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 0.21 | learning rate: 1.987E-04 | global batch size: 256 | lm loss: 3.486570E+00 | grad norm: 0.482 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.609 | TFLOPs: 7.91 | +31: iteration 2100/ 37905 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 0.21 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.479622E+00 | grad norm: 0.432 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.795 | TFLOPs: 7.71 | +31: iteration 2110/ 37905 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 0.20 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.462058E+00 | grad norm: 0.610 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.015 | TFLOPs: 8.07 | +31: iteration 2120/ 37905 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 0.23 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.486513E+00 | grad norm: 0.548 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.748 | TFLOPs: 6.95 | +31: iteration 2130/ 37905 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 0.19 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.486980E+00 | grad norm: 0.474 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1373.462 | TFLOPs: 8.75 | +31: iteration 2140/ 37905 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 0.19 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.479648E+00 | grad norm: 0.526 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1349.669 | TFLOPs: 8.60 | +31: iteration 2150/ 37905 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 0.20 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.472141E+00 | grad norm: 0.553 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.400 | TFLOPs: 8.24 | +31: iteration 2160/ 37905 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 0.19 | learning rate: 1.986E-04 | global batch size: 256 | lm loss: 3.479943E+00 | grad norm: 0.566 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.032 | TFLOPs: 8.45 | +31: iteration 2170/ 37905 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 0.20 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.492538E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.922 | TFLOPs: 8.02 | +31: iteration 2180/ 37905 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 0.19 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.499976E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1367.918 | TFLOPs: 8.71 | +31: iteration 2190/ 37905 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 0.22 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.474342E+00 | grad norm: 0.455 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.873 | TFLOPs: 7.55 | +31: iteration 2200/ 37905 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 0.20 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.498453E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.076 | TFLOPs: 8.35 | +31: iteration 2210/ 37905 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 0.21 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.447550E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.999 | TFLOPs: 7.85 | +31: iteration 2220/ 37905 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 0.21 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.525397E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.626 | TFLOPs: 7.59 | +31: iteration 2230/ 37905 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 0.23 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.471626E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.681 | TFLOPs: 7.07 | +31: iteration 2240/ 37905 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 0.19 | learning rate: 1.985E-04 | global batch size: 256 | lm loss: 3.499073E+00 | grad norm: 0.517 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1365.800 | TFLOPs: 8.70 | +31: iteration 2250/ 37905 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 0.21 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.455279E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.816 | TFLOPs: 7.62 | +31: iteration 2260/ 37905 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 0.19 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.424520E+00 | grad norm: 0.492 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.440 | TFLOPs: 8.63 | +31: iteration 2270/ 37905 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 0.20 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.425853E+00 | grad norm: 0.475 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1306.985 | TFLOPs: 8.32 | +31: iteration 2280/ 37905 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 0.20 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.449240E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1308.376 | TFLOPs: 8.33 | +31: iteration 2290/ 37905 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 0.20 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.485353E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.614 | TFLOPs: 8.11 | +31: iteration 2300/ 37905 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 0.20 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.457716E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.907 | TFLOPs: 8.12 | +31: iteration 2310/ 37905 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 0.22 | learning rate: 1.984E-04 | global batch size: 256 | lm loss: 3.476697E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.710 | TFLOPs: 7.44 | +31: iteration 2320/ 37905 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 0.21 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.470419E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.311 | TFLOPs: 7.92 | +31: iteration 2330/ 37905 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 0.19 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.398684E+00 | grad norm: 0.468 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1348.779 | TFLOPs: 8.59 | +31: iteration 2340/ 37905 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 0.20 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.417613E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.510 | TFLOPs: 8.16 | +31: iteration 2350/ 37905 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 0.20 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.447551E+00 | grad norm: 0.512 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1299.921 | TFLOPs: 8.28 | +31: iteration 2360/ 37905 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 0.20 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.466187E+00 | grad norm: 0.439 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.660 | TFLOPs: 8.09 | +31: iteration 2370/ 37905 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 0.20 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.474498E+00 | grad norm: 0.493 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1292.182 | TFLOPs: 8.23 | +31: iteration 2380/ 37905 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 0.20 | learning rate: 1.983E-04 | global batch size: 256 | lm loss: 3.449374E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.002 | TFLOPs: 8.31 | +31: iteration 2390/ 37905 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 0.20 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.439716E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.369 | TFLOPs: 8.07 | +31: iteration 2400/ 37905 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 0.19 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.486314E+00 | grad norm: 0.593 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1381.606 | TFLOPs: 8.80 | +31: iteration 2410/ 37905 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 0.18 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.454497E+00 | grad norm: 0.536 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1428.814 | TFLOPs: 9.10 | +31: iteration 2420/ 37905 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 0.20 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.440033E+00 | grad norm: 0.483 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.220 | TFLOPs: 8.33 | +31: iteration 2430/ 37905 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 0.19 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.444884E+00 | grad norm: 0.450 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1344.932 | TFLOPs: 8.57 | +31: iteration 2440/ 37905 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 0.20 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.415624E+00 | grad norm: 0.430 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.781 | TFLOPs: 8.09 | +31: iteration 2450/ 37905 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 0.23 | learning rate: 1.982E-04 | global batch size: 256 | lm loss: 3.442509E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.119 | TFLOPs: 7.13 | +31: iteration 2460/ 37905 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 0.25 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.468147E+00 | grad norm: 0.551 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.439 | TFLOPs: 6.63 | +31: iteration 2470/ 37905 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 0.23 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.433419E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.088 | TFLOPs: 6.96 | +31: iteration 2480/ 37905 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 0.21 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.410664E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1248.707 | TFLOPs: 7.95 | +31: iteration 2490/ 37905 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 0.21 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.409790E+00 | grad norm: 0.520 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.818 | TFLOPs: 7.73 | +31: iteration 2500/ 37905 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 0.19 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.440118E+00 | grad norm: 0.491 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1357.849 | TFLOPs: 8.65 | +31: iteration 2510/ 37905 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 0.21 | learning rate: 1.981E-04 | global batch size: 256 | lm loss: 3.453544E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.148 | TFLOPs: 7.91 | +31: iteration 2520/ 37905 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 0.21 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.407172E+00 | grad norm: 0.477 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.813 | TFLOPs: 7.67 | +31: iteration 2530/ 37905 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 0.21 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.421539E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.049 | TFLOPs: 7.62 | +31: iteration 2540/ 37905 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 0.23 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.402730E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.834 | TFLOPs: 7.22 | +31: iteration 2550/ 37905 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 0.21 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.373921E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.356 | TFLOPs: 7.74 | +31: iteration 2560/ 37905 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 0.20 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.396204E+00 | grad norm: 0.562 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.477 | TFLOPs: 8.24 | +31: iteration 2570/ 37905 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 0.20 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.408760E+00 | grad norm: 0.509 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.311 | TFLOPs: 8.22 | +31: iteration 2580/ 37905 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 0.22 | learning rate: 1.980E-04 | global batch size: 256 | lm loss: 3.414888E+00 | grad norm: 0.562 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.686 | TFLOPs: 7.58 | +31: iteration 2590/ 37905 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 0.19 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.438398E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1372.800 | TFLOPs: 8.74 | +31: iteration 2600/ 37905 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 0.22 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.381756E+00 | grad norm: 0.563 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.077 | TFLOPs: 7.53 | +31: iteration 2610/ 37905 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 0.20 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.426972E+00 | grad norm: 0.496 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.853 | TFLOPs: 8.14 | +31: iteration 2620/ 37905 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 0.20 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.435023E+00 | grad norm: 0.474 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.022 | TFLOPs: 8.05 | +31: iteration 2630/ 37905 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 0.21 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.408653E+00 | grad norm: 0.525 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.174 | TFLOPs: 7.74 | +31: iteration 2640/ 37905 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 0.22 | learning rate: 1.979E-04 | global batch size: 256 | lm loss: 3.458926E+00 | grad norm: 0.534 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1180.335 | TFLOPs: 7.52 | +31: iteration 2650/ 37905 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 0.23 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.424399E+00 | grad norm: 0.503 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.020 | TFLOPs: 7.02 | +31: iteration 2660/ 37905 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 0.19 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.396475E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.936 | TFLOPs: 8.69 | +31: iteration 2670/ 37905 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 0.22 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.402709E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.763 | TFLOPs: 7.42 | +31: iteration 2680/ 37905 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 0.19 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.365831E+00 | grad norm: 0.453 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.420 | TFLOPs: 8.36 | +31: iteration 2690/ 37905 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 0.20 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.390997E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.729 | TFLOPs: 8.14 | +31: iteration 2700/ 37905 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 0.19 | learning rate: 1.978E-04 | global batch size: 256 | lm loss: 3.404883E+00 | grad norm: 0.416 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.279 | TFLOPs: 8.39 | +31: iteration 2710/ 37905 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 0.22 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.360081E+00 | grad norm: 0.462 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.565 | TFLOPs: 7.49 | +31: iteration 2720/ 37905 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 0.19 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.424911E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1376.574 | TFLOPs: 8.77 | +31: iteration 2730/ 37905 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 0.19 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.385232E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.952 | TFLOPs: 8.38 | +31: iteration 2740/ 37905 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 0.18 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.357899E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1440.566 | TFLOPs: 9.17 | +31: iteration 2750/ 37905 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 0.21 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.366336E+00 | grad norm: 0.522 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.713 | TFLOPs: 7.82 | +31: iteration 2760/ 37905 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 0.21 | learning rate: 1.977E-04 | global batch size: 256 | lm loss: 3.385798E+00 | grad norm: 0.546 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.473 | TFLOPs: 7.75 | +31: iteration 2770/ 37905 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 0.19 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.410909E+00 | grad norm: 0.457 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1355.254 | TFLOPs: 8.63 | +31: iteration 2780/ 37905 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 0.19 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.392107E+00 | grad norm: 0.467 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.674 | TFLOPs: 8.39 | +31: iteration 2790/ 37905 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 0.20 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.407027E+00 | grad norm: 0.506 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1257.764 | TFLOPs: 8.01 | +31: iteration 2800/ 37905 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 0.18 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.435447E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1433.478 | TFLOPs: 9.13 | +31: iteration 2810/ 37905 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 0.20 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.351000E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.281 | TFLOPs: 8.15 | +31: iteration 2820/ 37905 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 0.20 | learning rate: 1.976E-04 | global batch size: 256 | lm loss: 3.428546E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.571 | TFLOPs: 8.17 | +31: iteration 2830/ 37905 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 0.18 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.420043E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1413.261 | TFLOPs: 9.00 | +31: iteration 2840/ 37905 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 0.21 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.374193E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.607 | TFLOPs: 7.68 | +31: iteration 2850/ 37905 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 0.18 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.393003E+00 | grad norm: 0.532 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1437.496 | TFLOPs: 9.16 | +31: iteration 2860/ 37905 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 0.20 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.392228E+00 | grad norm: 0.466 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.267 | TFLOPs: 8.24 | +31: iteration 2870/ 37905 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 0.24 | learning rate: 1.975E-04 | global batch size: 256 | lm loss: 3.399641E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.661 | TFLOPs: 6.91 | +31: iteration 2880/ 37905 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 0.19 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.388044E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1374.089 | TFLOPs: 8.75 | +31: iteration 2890/ 37905 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 0.21 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.368327E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.630 | TFLOPs: 7.61 | +31: iteration 2900/ 37905 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 0.22 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.368032E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.233 | TFLOPs: 7.31 | +31: iteration 2910/ 37905 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 0.22 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.382805E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.628 | TFLOPs: 7.44 | +31: iteration 2920/ 37905 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 0.22 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.339997E+00 | grad norm: 0.627 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.613 | TFLOPs: 7.43 | +31: iteration 2930/ 37905 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 0.22 | learning rate: 1.974E-04 | global batch size: 256 | lm loss: 3.338762E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.169 | TFLOPs: 7.29 | +31: iteration 2940/ 37905 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 0.22 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.349086E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.306 | TFLOPs: 7.47 | +31: iteration 2950/ 37905 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 0.21 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.343747E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.380 | TFLOPs: 7.69 | +31: iteration 2960/ 37905 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 0.22 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.397948E+00 | grad norm: 0.422 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.170 | TFLOPs: 7.48 | +31: iteration 2970/ 37905 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 0.21 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.411452E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.874 | TFLOPs: 7.83 | +31: iteration 2980/ 37905 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 0.19 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.382827E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1360.670 | TFLOPs: 8.67 | +31: iteration 2990/ 37905 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 0.20 | learning rate: 1.973E-04 | global batch size: 256 | lm loss: 3.369528E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1291.321 | TFLOPs: 8.22 | +31: iteration 3000/ 37905 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 0.21 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.367884E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.406 | TFLOPs: 7.73 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 3000 | lm loss value: 3.282038E+00 | lm loss PPL: 2.662998E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 3000 to checkpoints_83m + 0: [2022-11-24 14:24:05,972] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step3000 is begin to save! + 0: [2022-11-24 14:24:05,980] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,052] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,076] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,098] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,109] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,132] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,143] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,165] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:24:06,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:24:06,167] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step3000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:24:06,167] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:24:06,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:24:06,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step3000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 1: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +14: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:24:06,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +28: [2022-11-24 14:24:06,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:24:06,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:24:06,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +23: [2022-11-24 14:24:06,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:24:06,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +29: [2022-11-24 14:24:06,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:24:06,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +28: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 8: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:24:06,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +31: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +14: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:24:06,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 9: [2022-11-24 14:24:06,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:24:06,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +25: [2022-11-24 14:24:06,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +16: [2022-11-24 14:24:06,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +23: [2022-11-24 14:24:06,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 1: [2022-11-24 14:24:06,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +15: [2022-11-24 14:24:06,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:24:06,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:24:06,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +20: [2022-11-24 14:24:06,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:24:06,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 3: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 3: [2022-11-24 14:24:06,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +21: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:24:06,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 8: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +28: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +31: [2022-11-24 14:24:06,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:24:06,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +14: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:24:06,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 9: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 9: [2022-11-24 14:24:06,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:24:06,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +24: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:24:06,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +23: [2022-11-24 14:24:06,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:24:06,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 14:24:06,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +25: [2022-11-24 14:24:06,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:24:06,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +15: [2022-11-24 14:24:06,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:24:06,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:24:06,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:24:06,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:24:06,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +21: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +29: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 8: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:24:06,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +28: [2022-11-24 14:24:06,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +31: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:24:06,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +14: [2022-11-24 14:24:06,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 9: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:24:06,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 1: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +22: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 1: [2022-11-24 14:24:06,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:24:06,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +23: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:24:06,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +25: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:24:06,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:24:06,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:24:06,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:24:06,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +21: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +29: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:24:06,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:24:06,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 8: [2022-11-24 14:24:06,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:24:06,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +14: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 9: [2022-11-24 14:24:06,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:24:06,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 1: [2022-11-24 14:24:06,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +23: [2022-11-24 14:24:06,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:24:06,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:24:06,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:24:06,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +25: [2022-11-24 14:24:06,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +16: [2022-11-24 14:24:06,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 3: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:24:06,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:24:06,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +15: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:24:06,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +21: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:24:06,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +29: [2022-11-24 14:24:06,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:24:06,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 8: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +28: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +31: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:24:06,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +14: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:24:06,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 9: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:24:06,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:24:06,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +23: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:24:06,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +22: [2022-11-24 14:24:06,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:24:06,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 3: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +15: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:24:06,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:24:06,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +21: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:24:06,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:24:06,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 8: [2022-11-24 14:24:06,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +28: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +31: [2022-11-24 14:24:06,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +14: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:24:06,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +11: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +24: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 9: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 1: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:24:06,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:24:06,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:24:06,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:24:06,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 3: [2022-11-24 14:24:06,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +25: [2022-11-24 14:24:06,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:24:06,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:24:06,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +15: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:24:06,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:24:06,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +20: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +21: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +21: [2022-11-24 14:24:06,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +21: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +29: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +31: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +29: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 1: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +23: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +17: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +13: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +13: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +15: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +12: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +28: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +25: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +14: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 8: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +17: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +12: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +28: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +29: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +16: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +31: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +25: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 2: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +15: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 7: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 4: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +29: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 3: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +18: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +30: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +16: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +22: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 6: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +24: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +24: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 5: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +25: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +10: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +30: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +16: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +10: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +20: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +20: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +18: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +22: [2022-11-24 14:24:06,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +26: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +27: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:24:06,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 14:24:06,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! +19: [2022-11-24 14:24:06,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:24:06,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step3000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 14:24:06,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step3000 is ready now! + 0: successfully saved checkpoint at iteration 3000 to checkpoints_83m +31: time (ms) | save-checkpoint: 336.90 +31: iteration 3010/ 37905 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 0.24 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.349306E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.608 | TFLOPs: 6.88 | +31: iteration 3020/ 37905 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 0.21 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.368024E+00 | grad norm: 0.451 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.540 | TFLOPs: 7.60 | +31: iteration 3030/ 37905 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 0.22 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.314472E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.497 | TFLOPs: 7.48 | +31: iteration 3040/ 37905 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 0.19 | learning rate: 1.972E-04 | global batch size: 256 | lm loss: 3.365225E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.255 | TFLOPs: 8.41 | +31: iteration 3050/ 37905 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 0.19 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.378938E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.002 | TFLOPs: 8.50 | +31: iteration 3060/ 37905 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 0.19 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.394087E+00 | grad norm: 0.449 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1377.631 | TFLOPs: 8.77 | +31: iteration 3070/ 37905 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 0.20 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.397057E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.406 | TFLOPs: 8.31 | +31: iteration 3080/ 37905 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 0.19 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.352678E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.129 | TFLOPs: 8.38 | +31: iteration 3090/ 37905 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 0.20 | learning rate: 1.971E-04 | global batch size: 256 | lm loss: 3.357137E+00 | grad norm: 0.501 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.402 | TFLOPs: 8.07 | +31: iteration 3100/ 37905 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 0.20 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.393727E+00 | grad norm: 0.484 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.430 | TFLOPs: 8.14 | +31: iteration 3110/ 37905 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 0.20 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.320151E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.138 | TFLOPs: 8.06 | +31: iteration 3120/ 37905 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 0.18 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.361740E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1440.229 | TFLOPs: 9.17 | +31: iteration 3130/ 37905 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 0.22 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.361763E+00 | grad norm: 0.613 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.546 | TFLOPs: 7.54 | +31: iteration 3140/ 37905 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 0.19 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.324474E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.019 | TFLOPs: 8.38 | +31: iteration 3150/ 37905 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 0.20 | learning rate: 1.970E-04 | global batch size: 256 | lm loss: 3.374630E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.063 | TFLOPs: 8.35 | +31: iteration 3160/ 37905 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 0.20 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.318931E+00 | grad norm: 0.502 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.236 | TFLOPs: 8.18 | +31: iteration 3170/ 37905 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 0.19 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.332586E+00 | grad norm: 0.513 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.706 | TFLOPs: 8.39 | +31: iteration 3180/ 37905 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 0.24 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.357841E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.924 | TFLOPs: 6.80 | +31: iteration 3190/ 37905 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 0.23 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.310143E+00 | grad norm: 0.448 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.931 | TFLOPs: 7.15 | +31: iteration 3200/ 37905 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 0.19 | learning rate: 1.969E-04 | global batch size: 256 | lm loss: 3.318490E+00 | grad norm: 0.574 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.260 | TFLOPs: 8.55 | +31: iteration 3210/ 37905 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 0.21 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.369768E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.536 | TFLOPs: 7.77 | +31: iteration 3220/ 37905 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 0.23 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.335243E+00 | grad norm: 0.553 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.381 | TFLOPs: 7.00 | +31: iteration 3230/ 37905 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 0.21 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.360294E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.403 | TFLOPs: 7.93 | +31: iteration 3240/ 37905 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 0.23 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.325715E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.120 | TFLOPs: 7.12 | +31: iteration 3250/ 37905 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 0.20 | learning rate: 1.968E-04 | global batch size: 256 | lm loss: 3.299397E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.004 | TFLOPs: 7.97 | +31: iteration 3260/ 37905 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 0.21 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.337784E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.099 | TFLOPs: 7.66 | +31: iteration 3270/ 37905 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 0.21 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.348800E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.525 | TFLOPs: 7.68 | +31: iteration 3280/ 37905 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 0.22 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.328469E+00 | grad norm: 0.431 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.724 | TFLOPs: 7.39 | +31: iteration 3290/ 37905 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 0.21 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.295879E+00 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.370 | TFLOPs: 7.93 | +31: iteration 3300/ 37905 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 0.21 | learning rate: 1.967E-04 | global batch size: 256 | lm loss: 3.354682E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.655 | TFLOPs: 7.60 | +31: iteration 3310/ 37905 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 0.20 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.331573E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.350 | TFLOPs: 8.10 | +31: iteration 3320/ 37905 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 0.19 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.348412E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.363 | TFLOPs: 8.43 | +31: iteration 3330/ 37905 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 0.20 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.364082E+00 | grad norm: 0.619 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.519 | TFLOPs: 8.03 | +31: iteration 3340/ 37905 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 0.22 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.360604E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.769 | TFLOPs: 7.37 | +31: iteration 3350/ 37905 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 0.20 | learning rate: 1.966E-04 | global batch size: 256 | lm loss: 3.345714E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.945 | TFLOPs: 8.05 | +31: iteration 3360/ 37905 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 0.22 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.333443E+00 | grad norm: 0.452 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.114 | TFLOPs: 7.52 | +31: iteration 3370/ 37905 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 0.22 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.357916E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.095 | TFLOPs: 7.56 | +31: iteration 3380/ 37905 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 0.22 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.337088E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.979 | TFLOPs: 7.26 | +31: iteration 3390/ 37905 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 0.19 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.334954E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.128 | TFLOPs: 8.54 | +31: iteration 3400/ 37905 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 0.21 | learning rate: 1.965E-04 | global batch size: 256 | lm loss: 3.307351E+00 | grad norm: 0.516 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.227 | TFLOPs: 7.89 | +31: iteration 3410/ 37905 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 0.21 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.369003E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.446 | TFLOPs: 7.87 | +31: iteration 3420/ 37905 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 0.21 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.352235E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.998 | TFLOPs: 7.75 | +31: iteration 3430/ 37905 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 0.23 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.304101E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.538 | TFLOPs: 7.17 | +31: iteration 3440/ 37905 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 0.23 | learning rate: 1.964E-04 | global batch size: 256 | lm loss: 3.274021E+00 | grad norm: 0.469 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.205 | TFLOPs: 6.99 | +31: iteration 3450/ 37905 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 0.20 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.352858E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.886 | TFLOPs: 8.11 | +31: iteration 3460/ 37905 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 0.19 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.312540E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1370.963 | TFLOPs: 8.73 | +31: iteration 3470/ 37905 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 0.18 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.346280E+00 | grad norm: 0.466 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1442.317 | TFLOPs: 9.19 | +31: iteration 3480/ 37905 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 0.21 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.337319E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.972 | TFLOPs: 7.93 | +31: iteration 3490/ 37905 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 0.19 | learning rate: 1.963E-04 | global batch size: 256 | lm loss: 3.302396E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.718 | TFLOPs: 8.57 | +31: iteration 3500/ 37905 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 0.19 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.306502E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1369.911 | TFLOPs: 8.72 | +31: iteration 3510/ 37905 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 0.19 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.322186E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1362.831 | TFLOPs: 8.68 | +31: iteration 3520/ 37905 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 0.22 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.291970E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.226 | TFLOPs: 7.48 | +31: iteration 3530/ 37905 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 0.19 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.314963E+00 | grad norm: 0.533 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.570 | TFLOPs: 8.46 | +31: iteration 3540/ 37905 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 0.18 | learning rate: 1.962E-04 | global batch size: 256 | lm loss: 3.329876E+00 | grad norm: 0.444 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1423.068 | TFLOPs: 9.06 | +31: iteration 3550/ 37905 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 0.20 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.301513E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.028 | TFLOPs: 8.04 | +31: iteration 3560/ 37905 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 0.19 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.329282E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.478 | TFLOPs: 8.38 | +31: iteration 3570/ 37905 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 0.20 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.316854E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.225 | TFLOPs: 8.31 | +31: iteration 3580/ 37905 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 0.20 | learning rate: 1.961E-04 | global batch size: 256 | lm loss: 3.331132E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1300.312 | TFLOPs: 8.28 | +31: iteration 3590/ 37905 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 0.22 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.289062E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.090 | TFLOPs: 7.43 | +31: iteration 3600/ 37905 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 0.21 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.308825E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.087 | TFLOPs: 7.94 | +31: iteration 3610/ 37905 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 0.18 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.331941E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1436.470 | TFLOPs: 9.15 | +31: iteration 3620/ 37905 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 0.21 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.297182E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.339 | TFLOPs: 7.91 | +31: iteration 3630/ 37905 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 0.22 | learning rate: 1.960E-04 | global batch size: 256 | lm loss: 3.326694E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.493 | TFLOPs: 7.47 | +31: iteration 3640/ 37905 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 0.20 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.338129E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.339 | TFLOPs: 8.33 | +31: iteration 3650/ 37905 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 0.19 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.295319E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.358 | TFLOPs: 8.38 | +31: iteration 3660/ 37905 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 0.21 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.300579E+00 | grad norm: 0.408 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.109 | TFLOPs: 7.59 | +31: iteration 3670/ 37905 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 0.20 | learning rate: 1.959E-04 | global batch size: 256 | lm loss: 3.295079E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1248.994 | TFLOPs: 7.95 | +31: iteration 3680/ 37905 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 0.20 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.329881E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.971 | TFLOPs: 8.26 | +31: iteration 3690/ 37905 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 0.19 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.324205E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.488 | TFLOPs: 8.44 | +31: iteration 3700/ 37905 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 0.21 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.301616E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.237 | TFLOPs: 7.89 | +31: iteration 3710/ 37905 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 0.20 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.315700E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1309.466 | TFLOPs: 8.34 | +31: iteration 3720/ 37905 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 0.19 | learning rate: 1.958E-04 | global batch size: 256 | lm loss: 3.320220E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.202 | TFLOPs: 8.36 | +31: iteration 3730/ 37905 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 0.19 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.312332E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1344.357 | TFLOPs: 8.56 | +31: iteration 3740/ 37905 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 0.23 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.289568E+00 | grad norm: 0.406 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.194 | TFLOPs: 7.10 | +31: iteration 3750/ 37905 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 0.20 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.331353E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1302.679 | TFLOPs: 8.30 | +31: iteration 3760/ 37905 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 0.19 | learning rate: 1.957E-04 | global batch size: 256 | lm loss: 3.275268E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1353.384 | TFLOPs: 8.62 | +31: iteration 3770/ 37905 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 0.18 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.303194E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1424.116 | TFLOPs: 9.07 | +31: iteration 3780/ 37905 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 0.19 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.298355E+00 | grad norm: 0.463 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1370.342 | TFLOPs: 8.73 | +31: iteration 3790/ 37905 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 0.19 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.312550E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.115 | TFLOPs: 8.38 | +31: iteration 3800/ 37905 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 0.19 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.312468E+00 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.643 | TFLOPs: 8.63 | +31: iteration 3810/ 37905 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 0.20 | learning rate: 1.956E-04 | global batch size: 256 | lm loss: 3.302224E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1257.846 | TFLOPs: 8.01 | +31: iteration 3820/ 37905 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 0.20 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.312229E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.094 | TFLOPs: 8.31 | +31: iteration 3830/ 37905 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 0.19 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.329712E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1314.978 | TFLOPs: 8.37 | +31: iteration 3840/ 37905 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 0.18 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.296122E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1443.271 | TFLOPs: 9.19 | +31: iteration 3850/ 37905 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 0.19 | learning rate: 1.955E-04 | global batch size: 256 | lm loss: 3.266758E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1377.054 | TFLOPs: 8.77 | +31: iteration 3860/ 37905 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 0.19 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.288984E+00 | grad norm: 0.433 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.103 | TFLOPs: 8.38 | +31: iteration 3870/ 37905 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 0.19 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.255009E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1371.381 | TFLOPs: 8.73 | +31: iteration 3880/ 37905 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 0.19 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.317003E+00 | grad norm: 0.437 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.487 | TFLOPs: 8.38 | +31: iteration 3890/ 37905 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 0.19 | learning rate: 1.954E-04 | global batch size: 256 | lm loss: 3.316621E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.385 | TFLOPs: 8.38 | +31: iteration 3900/ 37905 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 0.20 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.276223E+00 | grad norm: 0.415 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1297.649 | TFLOPs: 8.26 | +31: iteration 3910/ 37905 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 0.19 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.297113E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.138 | TFLOPs: 8.76 | +31: iteration 3920/ 37905 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 0.19 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.270509E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.013 | TFLOPs: 8.43 | +31: iteration 3930/ 37905 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 0.22 | learning rate: 1.953E-04 | global batch size: 256 | lm loss: 3.322416E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.341 | TFLOPs: 7.54 | +31: iteration 3940/ 37905 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 0.20 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.250364E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.288 | TFLOPs: 8.17 | +31: iteration 3950/ 37905 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 0.21 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.282043E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.923 | TFLOPs: 7.94 | +31: iteration 3960/ 37905 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 0.22 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.249681E+00 | grad norm: 0.423 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.203 | TFLOPs: 7.30 | +31: iteration 3970/ 37905 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 0.25 | learning rate: 1.952E-04 | global batch size: 256 | lm loss: 3.317049E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.874 | TFLOPs: 6.51 | +31: iteration 3980/ 37905 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 0.18 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.293459E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1440.724 | TFLOPs: 9.18 | +31: iteration 3990/ 37905 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 0.20 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.308048E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1302.070 | TFLOPs: 8.29 | + 0: [2022-11-24 14:27:28,338] [INFO] [logging.py:68:log_dist] [Rank 0] step=4000, skipped=0, lr=[0.00019509932335081735, 0.00019509932335081735, 0.00019509932335081735], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 4000/ 37905 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 0.20 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.262840E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1299.892 | TFLOPs: 8.28 | + 0: steps: 4000 loss: 3.2033 iter time (s): 0.201 samples/sec: 1273.507 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 4000 | lm loss value: 3.313729E+00 | lm loss PPL: 2.748744E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 4000 to checkpoints_83m + 0: [2022-11-24 14:27:28,422] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step4000 is begin to save! + 0: [2022-11-24 14:27:28,430] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,515] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,526] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,537] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,560] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,594] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,605] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:27:28,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:27:28,618] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step4000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:27:28,618] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:27:28,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:27:28,684] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:27:28,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,690] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:27:28,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,691] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,691] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,691] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:27:28,692] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,692] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:27:28,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,693] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:27:28,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +18: [2022-11-24 14:27:28,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +12: [2022-11-24 14:27:28,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,694] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,695] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:27:28,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +13: [2022-11-24 14:27:28,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:27:28,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +10: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:27:28,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,696] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +28: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,697] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:27:28,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,698] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,698] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +15: [2022-11-24 14:27:28,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 14:27:28,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,699] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +15: [2022-11-24 14:27:28,699] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +23: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +18: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,700] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:27:28,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:27:28,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +24: [2022-11-24 14:27:28,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,701] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:27:28,701] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +12: [2022-11-24 14:27:28,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 3: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:27:28,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,702] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:27:28,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +27: [2022-11-24 14:27:28,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:27:28,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,703] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:27:28,703] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:27:28,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:27:28,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,704] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +28: [2022-11-24 14:27:28,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,704] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:27:28,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:27:28,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:27:28,706] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,706] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +18: [2022-11-24 14:27:28,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:27:28,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:27:28,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +24: [2022-11-24 14:27:28,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:27:28,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +12: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 3: [2022-11-24 14:27:28,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:27:28,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 1: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:27:28,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:27:28,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +27: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:27:28,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +10: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +28: [2022-11-24 14:27:28,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:27:28,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:27:28,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +15: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:27:28,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:27:28,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +30: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +18: [2022-11-24 14:27:28,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:27:28,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +24: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +12: [2022-11-24 14:27:28,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 3: [2022-11-24 14:27:28,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:27:28,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:27:28,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 1: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +27: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:27:28,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:27:28,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:27:28,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +10: [2022-11-24 14:27:28,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:27:28,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +15: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +28: [2022-11-24 14:27:28,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:27:28,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:27:28,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:27:28,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:27:28,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +30: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +18: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +24: [2022-11-24 14:27:28,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:27:28,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +12: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 3: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:27:28,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 14:27:28,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +27: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:27:28,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +15: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +15: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +28: [2022-11-24 14:27:28,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +15: [2022-11-24 14:27:28,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:27:28,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:27:28,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:27:28,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:27:28,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +30: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +18: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +11: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +24: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:27:28,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:27:28,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 3: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:27:28,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +13: [2022-11-24 14:27:28,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 1: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +27: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:27:28,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:27:28,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 14:27:28,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:27:28,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:27:28,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:27:28,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +28: [2022-11-24 14:27:28,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:27:28,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: [2022-11-24 14:27:28,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:27:28,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:27:28,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:27:28,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 6: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +30: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:27:28,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +18: [2022-11-24 14:27:28,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 14:27:28,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:27:28,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +24: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +12: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:27:28,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 14:27:28,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +29: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 3: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 8: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +18: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +29: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +11: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +12: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +28: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +10: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +30: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +30: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 1: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 2: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +12: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +27: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +22: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +15: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +24: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +25: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +22: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +14: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 3: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 4: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +24: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +21: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 5: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +25: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +21: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +31: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +19: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +20: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +15: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +23: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +27: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +10: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +19: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +20: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 7: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 9: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +31: [2022-11-24 14:27:28,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:27:28,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +17: [2022-11-24 14:27:28,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 14:27:28,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +16: [2022-11-24 14:27:28,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +26: [2022-11-24 14:27:28,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:27:28,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:27:28,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! +13: [2022-11-24 14:27:28,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:27:28,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step4000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 14:27:28,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step4000 is ready now! + 0: successfully saved checkpoint at iteration 4000 to checkpoints_83m +31: time (ms) | save-checkpoint: 320.57 +31: iteration 4010/ 37905 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 0.24 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.274248E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.697 | TFLOPs: 6.80 | +31: iteration 4020/ 37905 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 0.20 | learning rate: 1.951E-04 | global batch size: 256 | lm loss: 3.310575E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1298.715 | TFLOPs: 8.27 | +31: iteration 4030/ 37905 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 0.21 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.272368E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.551 | TFLOPs: 7.70 | +31: iteration 4040/ 37905 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 0.24 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.242495E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.011 | TFLOPs: 6.80 | +31: iteration 4050/ 37905 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 0.19 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.257281E+00 | grad norm: 0.531 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.742 | TFLOPs: 8.44 | +31: iteration 4060/ 37905 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 0.21 | learning rate: 1.950E-04 | global batch size: 256 | lm loss: 3.303094E+00 | grad norm: 0.479 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.339 | TFLOPs: 7.73 | +31: iteration 4070/ 37905 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 0.20 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.308838E+00 | grad norm: 0.411 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.145 | TFLOPs: 8.24 | +31: iteration 4080/ 37905 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 0.21 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.280035E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.400 | TFLOPs: 7.91 | +31: iteration 4090/ 37905 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 0.21 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.283634E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.978 | TFLOPs: 7.88 | +31: iteration 4100/ 37905 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 0.19 | learning rate: 1.949E-04 | global batch size: 256 | lm loss: 3.273219E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.083 | TFLOPs: 8.38 | +31: iteration 4110/ 37905 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 0.19 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.237954E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.763 | TFLOPs: 8.41 | +31: iteration 4120/ 37905 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 0.21 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.230567E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.118 | TFLOPs: 7.76 | +31: iteration 4130/ 37905 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 0.22 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.233549E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.093 | TFLOPs: 7.32 | +31: iteration 4140/ 37905 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 0.20 | learning rate: 1.948E-04 | global batch size: 256 | lm loss: 3.259529E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.492 | TFLOPs: 8.21 | +31: iteration 4150/ 37905 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 0.19 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.277244E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.239 | TFLOPs: 8.38 | +31: iteration 4160/ 37905 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 0.21 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.273876E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.794 | TFLOPs: 7.80 | +31: iteration 4170/ 37905 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 0.21 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.249050E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.755 | TFLOPs: 7.69 | +31: iteration 4180/ 37905 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 0.19 | learning rate: 1.947E-04 | global batch size: 256 | lm loss: 3.264626E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1376.148 | TFLOPs: 8.76 | +31: iteration 4190/ 37905 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 0.23 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.228100E+00 | grad norm: 0.508 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.316 | TFLOPs: 6.98 | +31: iteration 4200/ 37905 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 0.20 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.269504E+00 | grad norm: 0.401 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.256 | TFLOPs: 8.33 | +31: iteration 4210/ 37905 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 0.20 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.267182E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.908 | TFLOPs: 8.05 | +31: iteration 4220/ 37905 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 0.19 | learning rate: 1.946E-04 | global batch size: 256 | lm loss: 3.285536E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.039 | TFLOPs: 8.44 | +31: iteration 4230/ 37905 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 0.23 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.268344E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.178 | TFLOPs: 7.13 | +31: iteration 4240/ 37905 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 0.20 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.263190E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.836 | TFLOPs: 8.18 | +31: iteration 4250/ 37905 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 0.19 | learning rate: 1.945E-04 | global batch size: 256 | lm loss: 3.241585E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.107 | TFLOPs: 8.62 | +31: iteration 4260/ 37905 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 0.19 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.271687E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.212 | TFLOPs: 8.39 | +31: iteration 4270/ 37905 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 0.21 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.225638E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.199 | TFLOPs: 7.72 | +31: iteration 4280/ 37905 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 0.19 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.268796E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1362.889 | TFLOPs: 8.68 | +31: iteration 4290/ 37905 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 0.20 | learning rate: 1.944E-04 | global batch size: 256 | lm loss: 3.252840E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.512 | TFLOPs: 8.18 | +31: iteration 4300/ 37905 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 0.19 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.268282E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1318.839 | TFLOPs: 8.40 | +31: iteration 4310/ 37905 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 0.19 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.257075E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1318.072 | TFLOPs: 8.39 | +31: iteration 4320/ 37905 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 0.18 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.252124E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1443.528 | TFLOPs: 9.19 | +31: iteration 4330/ 37905 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 0.20 | learning rate: 1.943E-04 | global batch size: 256 | lm loss: 3.220561E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1308.515 | TFLOPs: 8.33 | +31: iteration 4340/ 37905 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 0.19 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.288657E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.703 | TFLOPs: 8.49 | +31: iteration 4350/ 37905 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 0.21 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.261927E+00 | grad norm: 0.426 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.919 | TFLOPs: 7.95 | +31: iteration 4360/ 37905 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 0.21 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.252491E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.640 | TFLOPs: 7.74 | +31: iteration 4370/ 37905 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 0.20 | learning rate: 1.942E-04 | global batch size: 256 | lm loss: 3.284350E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1309.850 | TFLOPs: 8.34 | +31: iteration 4380/ 37905 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 0.21 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.247378E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.130 | TFLOPs: 7.92 | +31: iteration 4390/ 37905 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 0.20 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.287898E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1260.519 | TFLOPs: 8.03 | +31: iteration 4400/ 37905 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 0.19 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.267131E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.581 | TFLOPs: 8.76 | +31: iteration 4410/ 37905 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 0.20 | learning rate: 1.941E-04 | global batch size: 256 | lm loss: 3.236829E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.661 | TFLOPs: 8.36 | +31: iteration 4420/ 37905 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 0.21 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.251115E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.688 | TFLOPs: 7.72 | +31: iteration 4430/ 37905 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 0.23 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.219946E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.311 | TFLOPs: 7.10 | +31: iteration 4440/ 37905 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 0.21 | learning rate: 1.940E-04 | global batch size: 256 | lm loss: 3.261948E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.433 | TFLOPs: 7.63 | +31: iteration 4450/ 37905 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 0.23 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.269750E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.374 | TFLOPs: 7.08 | +31: iteration 4460/ 37905 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 0.20 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.190201E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.151 | TFLOPs: 8.17 | +31: iteration 4470/ 37905 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 0.20 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.240069E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.704 | TFLOPs: 8.26 | +31: iteration 4480/ 37905 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 0.19 | learning rate: 1.939E-04 | global batch size: 256 | lm loss: 3.258770E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1358.387 | TFLOPs: 8.65 | +31: iteration 4490/ 37905 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 0.20 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.209516E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1306.807 | TFLOPs: 8.32 | +31: iteration 4500/ 37905 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 0.19 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.246635E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.061 | TFLOPs: 8.55 | +31: iteration 4510/ 37905 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 0.19 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.222731E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1314.913 | TFLOPs: 8.37 | +31: iteration 4520/ 37905 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 0.20 | learning rate: 1.938E-04 | global batch size: 256 | lm loss: 3.249091E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1260.368 | TFLOPs: 8.03 | +31: iteration 4530/ 37905 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 0.19 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.272160E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.334 | TFLOPs: 8.36 | +31: iteration 4540/ 37905 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 0.20 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.259049E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.690 | TFLOPs: 8.36 | +31: iteration 4550/ 37905 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 0.20 | learning rate: 1.937E-04 | global batch size: 256 | lm loss: 3.227577E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1310.969 | TFLOPs: 8.35 | +31: iteration 4560/ 37905 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 0.23 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.244889E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.424 | TFLOPs: 7.10 | +31: iteration 4570/ 37905 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 0.22 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.228319E+00 | grad norm: 0.461 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.028 | TFLOPs: 7.48 | +31: iteration 4580/ 37905 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 0.21 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.253845E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.972 | TFLOPs: 7.93 | +31: iteration 4590/ 37905 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 0.20 | learning rate: 1.936E-04 | global batch size: 256 | lm loss: 3.196088E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.810 | TFLOPs: 8.02 | +31: iteration 4600/ 37905 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 0.19 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.269527E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.240 | TFLOPs: 8.41 | +31: iteration 4610/ 37905 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 0.21 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.239455E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.795 | TFLOPs: 7.83 | +31: iteration 4620/ 37905 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 0.20 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.245930E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1287.388 | TFLOPs: 8.20 | +31: iteration 4630/ 37905 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 0.20 | learning rate: 1.935E-04 | global batch size: 256 | lm loss: 3.261822E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.732 | TFLOPs: 8.22 | +31: iteration 4640/ 37905 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 0.23 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.274951E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.485 | TFLOPs: 7.22 | +31: iteration 4650/ 37905 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 0.18 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.227452E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1398.303 | TFLOPs: 8.91 | +31: iteration 4660/ 37905 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 0.18 | learning rate: 1.934E-04 | global batch size: 256 | lm loss: 3.228065E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1442.792 | TFLOPs: 9.19 | +31: iteration 4670/ 37905 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 0.20 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.202907E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1299.136 | TFLOPs: 8.27 | +31: iteration 4680/ 37905 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 0.20 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.224999E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.891 | TFLOPs: 8.36 | +31: iteration 4690/ 37905 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 0.20 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.253399E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.855 | TFLOPs: 8.14 | +31: iteration 4700/ 37905 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 0.22 | learning rate: 1.933E-04 | global batch size: 256 | lm loss: 3.233340E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1180.212 | TFLOPs: 7.52 | +31: iteration 4710/ 37905 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 0.23 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.211413E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.671 | TFLOPs: 6.96 | +31: iteration 4720/ 37905 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 0.19 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.230696E+00 | grad norm: 0.503 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.487 | TFLOPs: 8.44 | +31: iteration 4730/ 37905 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 0.18 | learning rate: 1.932E-04 | global batch size: 256 | lm loss: 3.205802E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1426.629 | TFLOPs: 9.09 | +31: iteration 4740/ 37905 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 0.20 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.230908E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.914 | TFLOPs: 8.15 | +31: iteration 4750/ 37905 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 0.20 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.219827E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1306.196 | TFLOPs: 8.32 | +31: iteration 4760/ 37905 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 0.22 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.234282E+00 | grad norm: 0.498 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.414 | TFLOPs: 7.46 | +31: iteration 4770/ 37905 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 0.19 | learning rate: 1.931E-04 | global batch size: 256 | lm loss: 3.259772E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.276 | TFLOPs: 8.78 | +31: iteration 4780/ 37905 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 0.19 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.213814E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1376.376 | TFLOPs: 8.77 | +31: iteration 4790/ 37905 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 0.19 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.236025E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.881 | TFLOPs: 8.76 | +31: iteration 4800/ 37905 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 0.22 | learning rate: 1.930E-04 | global batch size: 256 | lm loss: 3.249371E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.862 | TFLOPs: 7.33 | +31: iteration 4810/ 37905 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 0.19 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.239441E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1380.794 | TFLOPs: 8.79 | +31: iteration 4820/ 37905 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 0.19 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.217740E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1382.372 | TFLOPs: 8.80 | +31: iteration 4830/ 37905 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 0.19 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.205495E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1351.201 | TFLOPs: 8.61 | +31: iteration 4840/ 37905 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 0.19 | learning rate: 1.929E-04 | global batch size: 256 | lm loss: 3.183111E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1365.736 | TFLOPs: 8.70 | +31: iteration 4850/ 37905 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 0.20 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.215152E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.864 | TFLOPs: 7.99 | +31: iteration 4860/ 37905 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 0.20 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.257105E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.356 | TFLOPs: 8.00 | +31: iteration 4870/ 37905 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 0.20 | learning rate: 1.928E-04 | global batch size: 256 | lm loss: 3.208660E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1310.045 | TFLOPs: 8.34 | +31: iteration 4880/ 37905 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 0.21 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.260026E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.868 | TFLOPs: 7.74 | +31: iteration 4890/ 37905 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 0.18 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.233123E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1398.079 | TFLOPs: 8.90 | +31: iteration 4900/ 37905 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 0.19 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.199397E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1357.294 | TFLOPs: 8.64 | +31: iteration 4910/ 37905 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 0.22 | learning rate: 1.927E-04 | global batch size: 256 | lm loss: 3.187934E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.510 | TFLOPs: 7.52 | +31: iteration 4920/ 37905 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 0.21 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.240998E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.507 | TFLOPs: 7.72 | +31: iteration 4930/ 37905 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 0.21 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.212265E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.285 | TFLOPs: 7.68 | +31: iteration 4940/ 37905 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 0.24 | learning rate: 1.926E-04 | global batch size: 256 | lm loss: 3.220583E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.560 | TFLOPs: 6.77 | +31: iteration 4950/ 37905 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 0.19 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.255109E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.210 | TFLOPs: 8.58 | +31: iteration 4960/ 37905 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 0.18 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.221119E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.294 | TFLOPs: 8.95 | +31: iteration 4970/ 37905 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 0.21 | learning rate: 1.925E-04 | global batch size: 256 | lm loss: 3.211878E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.030 | TFLOPs: 7.83 | +31: iteration 4980/ 37905 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 0.23 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.226737E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.028 | TFLOPs: 7.23 | +31: iteration 4990/ 37905 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 0.19 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.201104E+00 | grad norm: 0.425 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1371.940 | TFLOPs: 8.74 | +31: iteration 5000/ 37905 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 0.19 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.200330E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.403 | TFLOPs: 8.45 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 5000 | lm loss value: 3.213228E+00 | lm loss PPL: 2.485919E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 5000 to checkpoints_83m + 0: [2022-11-24 14:30:50,485] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step5000 is begin to save! + 0: [2022-11-24 14:30:50,493] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,565] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,577] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,588] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,611] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,622] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,633] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,656] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,678] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:30:50,679] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:30:50,679] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step5000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:30:50,679] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:30:50,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:30:50,746] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:30:50,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:30:50,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +17: [2022-11-24 14:30:50,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:30:50,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +25: [2022-11-24 14:30:50,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:30:50,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:30:50,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:30:50,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 8: [2022-11-24 14:30:50,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 5: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +22: [2022-11-24 14:30:50,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +22: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 7: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:30:50,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +17: [2022-11-24 14:30:50,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 2: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +19: [2022-11-24 14:30:50,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:30:50,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 4: [2022-11-24 14:30:50,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +18: [2022-11-24 14:30:50,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 4: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 1: [2022-11-24 14:30:50,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:30:50,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +25: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:30:50,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:30:50,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:30:50,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:30:50,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 5: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 8: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +22: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 7: [2022-11-24 14:30:50,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +17: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 3: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:30:50,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:30:50,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 2: [2022-11-24 14:30:50,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:30:50,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:30:50,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:30:50,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +18: [2022-11-24 14:30:50,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:30:50,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:30:50,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +19: [2022-11-24 14:30:50,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:30:50,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:30:50,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +25: [2022-11-24 14:30:50,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 1: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:30:50,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:30:50,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:30:50,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 8: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 7: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +22: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +22: [2022-11-24 14:30:50,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 3: [2022-11-24 14:30:50,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:30:50,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +17: [2022-11-24 14:30:50,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 4: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 4: [2022-11-24 14:30:50,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:30:50,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +23: [2022-11-24 14:30:50,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +18: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:30:50,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +19: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:30:50,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +25: [2022-11-24 14:30:50,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 1: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:30:50,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:30:50,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:30:50,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:30:50,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:30:50,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 8: [2022-11-24 14:30:50,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:30:50,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 5: [2022-11-24 14:30:50,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:30:50,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +22: [2022-11-24 14:30:50,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 3: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:30:50,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 7: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +17: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:30:50,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 2: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 4: [2022-11-24 14:30:50,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:30:50,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +23: [2022-11-24 14:30:50,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:30:50,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:30:50,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +19: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:30:50,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 1: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:30:50,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:30:50,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:30:50,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:30:50,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:30:50,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:30:50,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 5: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 8: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 3: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 3: [2022-11-24 14:30:50,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +17: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:30:50,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 7: [2022-11-24 14:30:50,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 2: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 4: [2022-11-24 14:30:50,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:30:50,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +18: [2022-11-24 14:30:50,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +19: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:30:50,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:30:50,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:30:50,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:30:50,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:30:50,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:30:50,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 5: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 8: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +22: [2022-11-24 14:30:50,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +22: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 3: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:30:50,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 7: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +17: [2022-11-24 14:30:50,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:30:50,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 2: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:30:50,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +18: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +19: [2022-11-24 14:30:50,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:30:50,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +25: [2022-11-24 14:30:50,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 1: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:30:50,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:30:50,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:30:50,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +15: [2022-11-24 14:30:50,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:30:50,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 8: [2022-11-24 14:30:50,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 5: [2022-11-24 14:30:50,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +17: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +11: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +11: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 9: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +12: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +10: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +15: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +21: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +23: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +12: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +10: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 4: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +18: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +28: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +30: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +22: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +24: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +18: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +30: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 2: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +23: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +29: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +31: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 2: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +23: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +29: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +19: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +22: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 1: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +13: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +20: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +26: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +24: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +16: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 6: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +26: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 5: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 1: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +14: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +13: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +31: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +16: [2022-11-24 14:30:50,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:30:50,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step5000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 14:30:50,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! +27: [2022-11-24 14:30:50,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step5000 is ready now! + 0: successfully saved checkpoint at iteration 5000 to checkpoints_83m +31: time (ms) | save-checkpoint: 319.67 +31: iteration 5010/ 37905 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 0.23 | learning rate: 1.924E-04 | global batch size: 256 | lm loss: 3.210036E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.766 | TFLOPs: 6.96 | +31: iteration 5020/ 37905 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 0.22 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.186446E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.477 | TFLOPs: 7.51 | +31: iteration 5030/ 37905 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 0.20 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.205346E+00 | grad norm: 0.600 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.446 | TFLOPs: 8.33 | +31: iteration 5040/ 37905 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 0.19 | learning rate: 1.923E-04 | global batch size: 256 | lm loss: 3.181628E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.552 | TFLOPs: 8.69 | +31: iteration 5050/ 37905 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 0.18 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.169877E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1410.239 | TFLOPs: 8.98 | +31: iteration 5060/ 37905 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 0.17 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.183172E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1480.421 | TFLOPs: 9.43 | +31: iteration 5070/ 37905 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 0.18 | learning rate: 1.922E-04 | global batch size: 256 | lm loss: 3.208969E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1406.938 | TFLOPs: 8.96 | +31: iteration 5080/ 37905 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 0.18 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.232503E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1411.101 | TFLOPs: 8.99 | +31: iteration 5090/ 37905 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 0.21 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.203716E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.224 | TFLOPs: 7.81 | +31: iteration 5100/ 37905 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 0.20 | learning rate: 1.921E-04 | global batch size: 256 | lm loss: 3.243022E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.620 | TFLOPs: 8.11 | +31: iteration 5110/ 37905 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 0.21 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.222092E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.217 | TFLOPs: 7.69 | +31: iteration 5120/ 37905 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 0.20 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.219418E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.420 | TFLOPs: 8.36 | +31: iteration 5130/ 37905 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 0.21 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.222700E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.575 | TFLOPs: 7.95 | +31: iteration 5140/ 37905 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 0.20 | learning rate: 1.920E-04 | global batch size: 256 | lm loss: 3.203944E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.976 | TFLOPs: 8.22 | +31: iteration 5150/ 37905 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 0.19 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.221889E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.720 | TFLOPs: 8.49 | +31: iteration 5160/ 37905 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 0.20 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.220708E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.352 | TFLOPs: 7.96 | +31: iteration 5170/ 37905 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 0.23 | learning rate: 1.919E-04 | global batch size: 256 | lm loss: 3.207701E+00 | grad norm: 0.377 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.374 | TFLOPs: 7.21 | +31: iteration 5180/ 37905 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 0.19 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.208106E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1331.850 | TFLOPs: 8.48 | +31: iteration 5190/ 37905 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 0.21 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.182233E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.556 | TFLOPs: 7.92 | +31: iteration 5200/ 37905 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 0.25 | learning rate: 1.918E-04 | global batch size: 256 | lm loss: 3.197544E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.162 | TFLOPs: 6.61 | +31: iteration 5210/ 37905 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 0.19 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.177200E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1370.561 | TFLOPs: 8.73 | +31: iteration 5220/ 37905 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 0.20 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.187912E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.280 | TFLOPs: 8.05 | +31: iteration 5230/ 37905 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 0.20 | learning rate: 1.917E-04 | global batch size: 256 | lm loss: 3.227260E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.889 | TFLOPs: 8.04 | +31: iteration 5240/ 37905 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 0.21 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.181872E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.947 | TFLOPs: 7.62 | +31: iteration 5250/ 37905 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 0.18 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.210313E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1436.909 | TFLOPs: 9.15 | +31: iteration 5260/ 37905 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 0.20 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.228617E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.925 | TFLOPs: 8.22 | +31: iteration 5270/ 37905 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 0.19 | learning rate: 1.916E-04 | global batch size: 256 | lm loss: 3.160861E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.489 | TFLOPs: 8.54 | +31: iteration 5280/ 37905 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 0.21 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.216338E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.858 | TFLOPs: 7.87 | +31: iteration 5290/ 37905 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 0.21 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.176275E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.462 | TFLOPs: 7.77 | +31: iteration 5300/ 37905 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 0.17 | learning rate: 1.915E-04 | global batch size: 256 | lm loss: 3.181892E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1482.281 | TFLOPs: 9.44 | +31: iteration 5310/ 37905 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 0.21 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.224020E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.742 | TFLOPs: 7.65 | +31: iteration 5320/ 37905 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 0.19 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.196675E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.256 | TFLOPs: 8.55 | +31: iteration 5330/ 37905 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 0.22 | learning rate: 1.914E-04 | global batch size: 256 | lm loss: 3.197270E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.728 | TFLOPs: 7.54 | +31: iteration 5340/ 37905 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 0.20 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.229455E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.639 | TFLOPs: 8.15 | +31: iteration 5350/ 37905 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 0.19 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.167554E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.864 | TFLOPs: 8.57 | +31: iteration 5360/ 37905 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 0.18 | learning rate: 1.913E-04 | global batch size: 256 | lm loss: 3.226351E+00 | grad norm: 0.378 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1456.534 | TFLOPs: 9.28 | +31: iteration 5370/ 37905 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 0.18 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.210331E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1387.268 | TFLOPs: 8.84 | +31: iteration 5380/ 37905 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 0.17 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.167804E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1481.962 | TFLOPs: 9.44 | +31: iteration 5390/ 37905 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 0.21 | learning rate: 1.912E-04 | global batch size: 256 | lm loss: 3.205676E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.276 | TFLOPs: 7.90 | +31: iteration 5400/ 37905 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 0.20 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.163321E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.420 | TFLOPs: 8.17 | +31: iteration 5410/ 37905 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 0.19 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.203375E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.328 | TFLOPs: 8.54 | +31: iteration 5420/ 37905 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 0.22 | learning rate: 1.911E-04 | global batch size: 256 | lm loss: 3.191939E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.652 | TFLOPs: 7.35 | +31: iteration 5430/ 37905 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 0.21 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.212503E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1230.119 | TFLOPs: 7.83 | +31: iteration 5440/ 37905 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 0.19 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.196577E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.302 | TFLOPs: 8.44 | +31: iteration 5450/ 37905 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 0.22 | learning rate: 1.910E-04 | global batch size: 256 | lm loss: 3.202082E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.657 | TFLOPs: 7.56 | +31: iteration 5460/ 37905 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 0.21 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.222649E+00 | grad norm: 0.447 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.854 | TFLOPs: 7.60 | +31: iteration 5470/ 37905 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 0.19 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.195692E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.101 | TFLOPs: 8.46 | +31: iteration 5480/ 37905 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 0.20 | learning rate: 1.909E-04 | global batch size: 256 | lm loss: 3.192554E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.678 | TFLOPs: 8.18 | +31: iteration 5490/ 37905 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 0.20 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.164523E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.499 | TFLOPs: 7.96 | +31: iteration 5500/ 37905 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 0.18 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.230485E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1406.078 | TFLOPs: 8.96 | +31: iteration 5510/ 37905 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 0.22 | learning rate: 1.908E-04 | global batch size: 256 | lm loss: 3.195795E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.857 | TFLOPs: 7.41 | +31: iteration 5520/ 37905 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 0.21 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.226241E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.013 | TFLOPs: 7.62 | +31: iteration 5530/ 37905 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 0.18 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.189841E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1406.836 | TFLOPs: 8.96 | +31: iteration 5540/ 37905 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 0.20 | learning rate: 1.907E-04 | global batch size: 256 | lm loss: 3.233928E+00 | grad norm: 0.365 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.775 | TFLOPs: 8.35 | +31: iteration 5550/ 37905 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 0.19 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.199247E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1322.939 | TFLOPs: 8.43 | +31: iteration 5560/ 37905 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 0.20 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.186914E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.751 | TFLOPs: 8.05 | +31: iteration 5570/ 37905 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 0.19 | learning rate: 1.906E-04 | global batch size: 256 | lm loss: 3.217982E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.189 | TFLOPs: 8.62 | +31: iteration 5580/ 37905 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 0.18 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.170764E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1387.385 | TFLOPs: 8.84 | +31: iteration 5590/ 37905 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 0.20 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.183671E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.128 | TFLOPs: 8.14 | +31: iteration 5600/ 37905 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 0.20 | learning rate: 1.905E-04 | global batch size: 256 | lm loss: 3.169269E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.211 | TFLOPs: 8.19 | +31: iteration 5610/ 37905 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 0.18 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.227585E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1387.173 | TFLOPs: 8.83 | +31: iteration 5620/ 37905 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 0.20 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.174956E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.671 | TFLOPs: 8.18 | +31: iteration 5630/ 37905 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 0.21 | learning rate: 1.904E-04 | global batch size: 256 | lm loss: 3.234378E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.701 | TFLOPs: 7.62 | +31: iteration 5640/ 37905 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 0.19 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.142073E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1322.997 | TFLOPs: 8.43 | +31: iteration 5650/ 37905 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 0.20 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.196353E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1300.021 | TFLOPs: 8.28 | +31: iteration 5660/ 37905 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 0.21 | learning rate: 1.903E-04 | global batch size: 256 | lm loss: 3.174273E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.710 | TFLOPs: 7.58 | +31: iteration 5670/ 37905 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 0.20 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.220084E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.216 | TFLOPs: 8.31 | +31: iteration 5680/ 37905 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 0.18 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.203249E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1455.574 | TFLOPs: 9.27 | +31: iteration 5690/ 37905 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 0.17 | learning rate: 1.902E-04 | global batch size: 256 | lm loss: 3.245885E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1482.807 | TFLOPs: 9.44 | +31: iteration 5700/ 37905 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 0.21 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.219517E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.060 | TFLOPs: 7.64 | +31: iteration 5710/ 37905 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 0.20 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.185024E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.996 | TFLOPs: 8.11 | +31: iteration 5720/ 37905 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 0.19 | learning rate: 1.901E-04 | global batch size: 256 | lm loss: 3.168685E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.095 | TFLOPs: 8.55 | +31: iteration 5730/ 37905 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 0.19 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.217707E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.808 | TFLOPs: 8.53 | +31: iteration 5740/ 37905 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 0.19 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.184608E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.826 | TFLOPs: 8.42 | +31: iteration 5750/ 37905 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 0.19 | learning rate: 1.900E-04 | global batch size: 256 | lm loss: 3.147706E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.471 | TFLOPs: 8.55 | +31: iteration 5760/ 37905 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 0.18 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.181354E+00 | grad norm: 0.390 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1404.219 | TFLOPs: 8.94 | +31: iteration 5770/ 37905 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 0.17 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.173249E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1476.731 | TFLOPs: 9.40 | +31: iteration 5780/ 37905 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 0.19 | learning rate: 1.899E-04 | global batch size: 256 | lm loss: 3.172045E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1369.033 | TFLOPs: 8.72 | +31: iteration 5790/ 37905 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 0.19 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.188114E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.535 | TFLOPs: 8.42 | +31: iteration 5800/ 37905 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 0.19 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.208632E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.691 | TFLOPs: 8.53 | +31: iteration 5810/ 37905 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 0.19 | learning rate: 1.898E-04 | global batch size: 256 | lm loss: 3.175129E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.252 | TFLOPs: 8.54 | +31: iteration 5820/ 37905 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 0.19 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.203741E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1355.004 | TFLOPs: 8.63 | +31: iteration 5830/ 37905 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 0.18 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.172446E+00 | grad norm: 0.417 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1409.073 | TFLOPs: 8.97 | +31: iteration 5840/ 37905 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 0.22 | learning rate: 1.897E-04 | global batch size: 256 | lm loss: 3.188326E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.019 | TFLOPs: 7.39 | +31: iteration 5850/ 37905 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 0.22 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.194641E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.242 | TFLOPs: 7.47 | +31: iteration 5860/ 37905 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 0.20 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.186349E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.902 | TFLOPs: 8.06 | +31: iteration 5870/ 37905 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 0.20 | learning rate: 1.896E-04 | global batch size: 256 | lm loss: 3.188163E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.862 | TFLOPs: 8.09 | +31: iteration 5880/ 37905 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 0.19 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.188317E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1361.857 | TFLOPs: 8.67 | +31: iteration 5890/ 37905 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 0.19 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.141589E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1331.718 | TFLOPs: 8.48 | +31: iteration 5900/ 37905 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 0.18 | learning rate: 1.895E-04 | global batch size: 256 | lm loss: 3.155271E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1407.262 | TFLOPs: 8.96 | +31: iteration 5910/ 37905 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 0.19 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.180354E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1336.542 | TFLOPs: 8.51 | +31: iteration 5920/ 37905 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 0.23 | learning rate: 1.894E-04 | global batch size: 256 | lm loss: 3.201575E+00 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.859 | TFLOPs: 7.18 | +31: iteration 5930/ 37905 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 0.20 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.179874E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.178 | TFLOPs: 8.14 | +31: iteration 5940/ 37905 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 0.22 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.179039E+00 | grad norm: 0.428 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.581 | TFLOPs: 7.30 | +31: iteration 5950/ 37905 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 0.21 | learning rate: 1.893E-04 | global batch size: 256 | lm loss: 3.189539E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.390 | TFLOPs: 7.88 | +31: iteration 5960/ 37905 | consumed samples: 1525760 | consumed tokens: 3124756480 | elapsed time per iteration (s): 0.21 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.190187E+00 | grad norm: 0.379 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.039 | TFLOPs: 7.92 | +31: iteration 5970/ 37905 | consumed samples: 1528320 | consumed tokens: 3129999360 | elapsed time per iteration (s): 0.19 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.225285E+00 | grad norm: 0.397 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.326 | TFLOPs: 8.45 | +31: iteration 5980/ 37905 | consumed samples: 1530880 | consumed tokens: 3135242240 | elapsed time per iteration (s): 0.19 | learning rate: 1.892E-04 | global batch size: 256 | lm loss: 3.186511E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.682 | TFLOPs: 8.45 | +31: iteration 5990/ 37905 | consumed samples: 1533440 | consumed tokens: 3140485120 | elapsed time per iteration (s): 0.19 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.197690E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.153 | TFLOPs: 8.57 | + 0: [2022-11-24 14:34:08,429] [INFO] [logging.py:68:log_dist] [Rank 0] step=6000, skipped=0, lr=[0.00018909936941176276, 0.00018909936941176276, 0.00018909936941176276], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 6000/ 37905 | consumed samples: 1536000 | consumed tokens: 3145728000 | elapsed time per iteration (s): 0.19 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.178903E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.384 | TFLOPs: 8.57 | + 0: steps: 6000 loss: 3.1969 iter time (s): 0.198 samples/sec: 1295.342 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 6000 | lm loss value: 3.168652E+00 | lm loss PPL: 2.377541E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 6000 to checkpoints_83m + 0: [2022-11-24 14:34:08,509] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step6000 is begin to save! + 0: [2022-11-24 14:34:08,518] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,591] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,604] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,615] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,626] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,659] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,681] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,703] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,703] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:34:08,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:34:08,705] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step6000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:34:08,705] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:34:08,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:34:08,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +15: [2022-11-24 14:34:08,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +15: [2022-11-24 14:34:08,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +15: [2022-11-24 14:34:08,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +17: [2022-11-24 14:34:08,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +18: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 3: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 14:34:08,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:34:08,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:34:08,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +12: [2022-11-24 14:34:08,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +26: [2022-11-24 14:34:08,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:34:08,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:34:08,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 6: [2022-11-24 14:34:08,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +21: [2022-11-24 14:34:08,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +19: [2022-11-24 14:34:08,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +19: [2022-11-24 14:34:08,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:34:08,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +27: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +15: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:34:08,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 8: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +25: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +17: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:34:08,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +18: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +23: [2022-11-24 14:34:08,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:34:08,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 1: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +28: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:34:08,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:34:08,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:34:08,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +22: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +16: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +12: [2022-11-24 14:34:08,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:34:08,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 6: [2022-11-24 14:34:08,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:34:08,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +15: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 8: [2022-11-24 14:34:08,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +27: [2022-11-24 14:34:08,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:34:08,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:34:08,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +17: [2022-11-24 14:34:08,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +25: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 1: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:34:08,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:34:08,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 3: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:34:08,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:34:08,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +26: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +12: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +23: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:34:08,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +23: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:34:08,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +16: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +16: [2022-11-24 14:34:08,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:34:08,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 6: [2022-11-24 14:34:08,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:34:08,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:34:08,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +15: [2022-11-24 14:34:08,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +15: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +27: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 8: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:34:08,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +17: [2022-11-24 14:34:08,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: [2022-11-24 14:34:08,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:34:08,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +25: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 1: [2022-11-24 14:34:08,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:34:08,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:34:08,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:34:08,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:34:08,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +26: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:34:08,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:34:08,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +12: [2022-11-24 14:34:08,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:34:08,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +19: [2022-11-24 14:34:08,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 6: [2022-11-24 14:34:08,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 14:34:08,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +15: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +15: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 8: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:34:08,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +27: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:34:08,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +17: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +25: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:34:08,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 1: [2022-11-24 14:34:08,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:34:08,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:34:08,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 3: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:34:08,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:34:08,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +26: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +16: [2022-11-24 14:34:08,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +12: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:34:08,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:34:08,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +19: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 6: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:34:08,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +15: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 8: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:34:08,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +17: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +18: [2022-11-24 14:34:08,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: [2022-11-24 14:34:08,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +25: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 1: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:34:08,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 14:34:08,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:34:08,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 3: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +26: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:34:08,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:34:08,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +24: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +16: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +16: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +23: [2022-11-24 14:34:08,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:34:08,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +12: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:34:08,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +19: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:34:08,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +21: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +15: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:34:08,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 8: [2022-11-24 14:34:08,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +27: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:34:08,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +17: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +25: [2022-11-24 14:34:08,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 1: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:34:08,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:34:08,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:34:08,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 7: [2022-11-24 14:34:08,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 3: [2022-11-24 14:34:08,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:34:08,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:34:08,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:34:08,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +26: [2022-11-24 14:34:08,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:34:08,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +23: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:34:08,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +19: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +12: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +24: [2022-11-24 14:34:08,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +15: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 5: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +25: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +11: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +12: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +29: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +30: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 8: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +29: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +30: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +16: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +23: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +11: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +16: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 6: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +17: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 9: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +19: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +22: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 1: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +21: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +31: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +19: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +14: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +26: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +28: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +27: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +10: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 2: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +14: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +21: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +18: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +31: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +22: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 4: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +27: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +20: [2022-11-24 14:34:08,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +23: [2022-11-24 14:34:08,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +27: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +20: [2022-11-24 14:34:08,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +23: [2022-11-24 14:34:08,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! +13: [2022-11-24 14:34:08,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:34:08,825] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step6000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 14:34:08,825] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step6000 is ready now! + 0: successfully saved checkpoint at iteration 6000 to checkpoints_83m +31: time (ms) | save-checkpoint: 320.60 +31: iteration 6010/ 37905 | consumed samples: 1538560 | consumed tokens: 3150970880 | elapsed time per iteration (s): 0.22 | learning rate: 1.891E-04 | global batch size: 256 | lm loss: 3.206598E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.834 | TFLOPs: 7.44 | +31: iteration 6020/ 37905 | consumed samples: 1541120 | consumed tokens: 3156213760 | elapsed time per iteration (s): 0.19 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.166954E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.047 | TFLOPs: 8.41 | +31: iteration 6030/ 37905 | consumed samples: 1543680 | consumed tokens: 3161456640 | elapsed time per iteration (s): 0.18 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.161723E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.723 | TFLOPs: 8.95 | +31: iteration 6040/ 37905 | consumed samples: 1546240 | consumed tokens: 3166699520 | elapsed time per iteration (s): 0.20 | learning rate: 1.890E-04 | global batch size: 256 | lm loss: 3.216086E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.220 | TFLOPs: 8.14 | +31: iteration 6050/ 37905 | consumed samples: 1548800 | consumed tokens: 3171942400 | elapsed time per iteration (s): 0.22 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.152905E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.159 | TFLOPs: 7.56 | +31: iteration 6060/ 37905 | consumed samples: 1551360 | consumed tokens: 3177185280 | elapsed time per iteration (s): 0.20 | learning rate: 1.889E-04 | global batch size: 256 | lm loss: 3.163743E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.298 | TFLOPs: 7.97 | +31: iteration 6070/ 37905 | consumed samples: 1553920 | consumed tokens: 3182428160 | elapsed time per iteration (s): 0.21 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.198593E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.260 | TFLOPs: 7.93 | +31: iteration 6080/ 37905 | consumed samples: 1556480 | consumed tokens: 3187671040 | elapsed time per iteration (s): 0.19 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.185512E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.225 | TFLOPs: 8.62 | +31: iteration 6090/ 37905 | consumed samples: 1559040 | consumed tokens: 3192913920 | elapsed time per iteration (s): 0.19 | learning rate: 1.888E-04 | global batch size: 256 | lm loss: 3.169494E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1374.000 | TFLOPs: 8.75 | +31: iteration 6100/ 37905 | consumed samples: 1561600 | consumed tokens: 3198156800 | elapsed time per iteration (s): 0.17 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.192830E+00 | grad norm: 0.414 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1481.248 | TFLOPs: 9.43 | +31: iteration 6110/ 37905 | consumed samples: 1564160 | consumed tokens: 3203399680 | elapsed time per iteration (s): 0.19 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.160242E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1337.137 | TFLOPs: 8.52 | +31: iteration 6120/ 37905 | consumed samples: 1566720 | consumed tokens: 3208642560 | elapsed time per iteration (s): 0.19 | learning rate: 1.887E-04 | global batch size: 256 | lm loss: 3.139115E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.500 | TFLOPs: 8.47 | +31: iteration 6130/ 37905 | consumed samples: 1569280 | consumed tokens: 3213885440 | elapsed time per iteration (s): 0.18 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.177779E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1419.521 | TFLOPs: 9.04 | +31: iteration 6140/ 37905 | consumed samples: 1571840 | consumed tokens: 3219128320 | elapsed time per iteration (s): 0.19 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.162365E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.880 | TFLOPs: 8.69 | +31: iteration 6150/ 37905 | consumed samples: 1574400 | consumed tokens: 3224371200 | elapsed time per iteration (s): 0.21 | learning rate: 1.886E-04 | global batch size: 256 | lm loss: 3.166896E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.587 | TFLOPs: 7.86 | +31: iteration 6160/ 37905 | consumed samples: 1576960 | consumed tokens: 3229614080 | elapsed time per iteration (s): 0.19 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.151877E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.941 | TFLOPs: 8.39 | +31: iteration 6170/ 37905 | consumed samples: 1579520 | consumed tokens: 3234856960 | elapsed time per iteration (s): 0.19 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.161529E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1355.593 | TFLOPs: 8.63 | +31: iteration 6180/ 37905 | consumed samples: 1582080 | consumed tokens: 3240099840 | elapsed time per iteration (s): 0.21 | learning rate: 1.885E-04 | global batch size: 256 | lm loss: 3.148101E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.116 | TFLOPs: 7.75 | +31: iteration 6190/ 37905 | consumed samples: 1584640 | consumed tokens: 3245342720 | elapsed time per iteration (s): 0.19 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.186473E+00 | grad norm: 0.363 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.039 | TFLOPs: 8.53 | +31: iteration 6200/ 37905 | consumed samples: 1587200 | consumed tokens: 3250585600 | elapsed time per iteration (s): 0.20 | learning rate: 1.884E-04 | global batch size: 256 | lm loss: 3.172593E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1257.898 | TFLOPs: 8.01 | +31: iteration 6210/ 37905 | consumed samples: 1589760 | consumed tokens: 3255828480 | elapsed time per iteration (s): 0.21 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.208018E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.241 | TFLOPs: 7.89 | +31: iteration 6220/ 37905 | consumed samples: 1592320 | consumed tokens: 3261071360 | elapsed time per iteration (s): 0.21 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.186753E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.589 | TFLOPs: 7.77 | +31: iteration 6230/ 37905 | consumed samples: 1594880 | consumed tokens: 3266314240 | elapsed time per iteration (s): 0.19 | learning rate: 1.883E-04 | global batch size: 256 | lm loss: 3.200762E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.098 | TFLOPs: 8.49 | +31: iteration 6240/ 37905 | consumed samples: 1597440 | consumed tokens: 3271557120 | elapsed time per iteration (s): 0.21 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.196535E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.950 | TFLOPs: 7.78 | +31: iteration 6250/ 37905 | consumed samples: 1600000 | consumed tokens: 3276800000 | elapsed time per iteration (s): 0.25 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.156139E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.264 | TFLOPs: 6.63 | +31: iteration 6260/ 37905 | consumed samples: 1602560 | consumed tokens: 3282042880 | elapsed time per iteration (s): 0.19 | learning rate: 1.882E-04 | global batch size: 256 | lm loss: 3.191192E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1314.060 | TFLOPs: 8.37 | +31: iteration 6270/ 37905 | consumed samples: 1605120 | consumed tokens: 3287285760 | elapsed time per iteration (s): 0.19 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.164135E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.678 | TFLOPs: 8.43 | +31: iteration 6280/ 37905 | consumed samples: 1607680 | consumed tokens: 3292528640 | elapsed time per iteration (s): 0.19 | learning rate: 1.881E-04 | global batch size: 256 | lm loss: 3.158303E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1381.590 | TFLOPs: 8.80 | +31: iteration 6290/ 37905 | consumed samples: 1610240 | consumed tokens: 3297771520 | elapsed time per iteration (s): 0.21 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.149664E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.531 | TFLOPs: 7.93 | +31: iteration 6300/ 37905 | consumed samples: 1612800 | consumed tokens: 3303014400 | elapsed time per iteration (s): 0.22 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.160858E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.276 | TFLOPs: 7.52 | +31: iteration 6310/ 37905 | consumed samples: 1615360 | consumed tokens: 3308257280 | elapsed time per iteration (s): 0.19 | learning rate: 1.880E-04 | global batch size: 256 | lm loss: 3.146600E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1339.848 | TFLOPs: 8.53 | +31: iteration 6320/ 37905 | consumed samples: 1617920 | consumed tokens: 3313500160 | elapsed time per iteration (s): 0.21 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 3.169052E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.436 | TFLOPs: 7.64 | +31: iteration 6330/ 37905 | consumed samples: 1620480 | consumed tokens: 3318743040 | elapsed time per iteration (s): 0.19 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 3.206189E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1370.184 | TFLOPs: 8.73 | +31: iteration 6340/ 37905 | consumed samples: 1623040 | consumed tokens: 3323985920 | elapsed time per iteration (s): 0.18 | learning rate: 1.879E-04 | global batch size: 256 | lm loss: 3.123955E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1456.916 | TFLOPs: 9.28 | +31: iteration 6350/ 37905 | consumed samples: 1625600 | consumed tokens: 3329228800 | elapsed time per iteration (s): 0.18 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.167526E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.814 | TFLOPs: 8.95 | +31: iteration 6360/ 37905 | consumed samples: 1628160 | consumed tokens: 3334471680 | elapsed time per iteration (s): 0.19 | learning rate: 1.878E-04 | global batch size: 256 | lm loss: 3.151295E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.087 | TFLOPs: 8.46 | +31: iteration 6370/ 37905 | consumed samples: 1630720 | consumed tokens: 3339714560 | elapsed time per iteration (s): 0.19 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.183447E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1377.993 | TFLOPs: 8.78 | +31: iteration 6380/ 37905 | consumed samples: 1633280 | consumed tokens: 3344957440 | elapsed time per iteration (s): 0.19 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.145934E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1369.065 | TFLOPs: 8.72 | +31: iteration 6390/ 37905 | consumed samples: 1635840 | consumed tokens: 3350200320 | elapsed time per iteration (s): 0.18 | learning rate: 1.877E-04 | global batch size: 256 | lm loss: 3.153637E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1415.849 | TFLOPs: 9.02 | +31: iteration 6400/ 37905 | consumed samples: 1638400 | consumed tokens: 3355443200 | elapsed time per iteration (s): 0.20 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.153193E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.587 | TFLOPs: 8.17 | +31: iteration 6410/ 37905 | consumed samples: 1640960 | consumed tokens: 3360686080 | elapsed time per iteration (s): 0.18 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.183146E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1386.706 | TFLOPs: 8.83 | +31: iteration 6420/ 37905 | consumed samples: 1643520 | consumed tokens: 3365928960 | elapsed time per iteration (s): 0.18 | learning rate: 1.876E-04 | global batch size: 256 | lm loss: 3.134936E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1425.496 | TFLOPs: 9.08 | +31: iteration 6430/ 37905 | consumed samples: 1646080 | consumed tokens: 3371171840 | elapsed time per iteration (s): 0.19 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.159153E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1349.935 | TFLOPs: 8.60 | +31: iteration 6440/ 37905 | consumed samples: 1648640 | consumed tokens: 3376414720 | elapsed time per iteration (s): 0.23 | learning rate: 1.875E-04 | global batch size: 256 | lm loss: 3.166088E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.689 | TFLOPs: 7.07 | +31: iteration 6450/ 37905 | consumed samples: 1651200 | consumed tokens: 3381657600 | elapsed time per iteration (s): 0.22 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.154230E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.025 | TFLOPs: 7.27 | +31: iteration 6460/ 37905 | consumed samples: 1653760 | consumed tokens: 3386900480 | elapsed time per iteration (s): 0.21 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.114075E+00 | grad norm: 0.375 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.889 | TFLOPs: 7.92 | +31: iteration 6470/ 37905 | consumed samples: 1656320 | consumed tokens: 3392143360 | elapsed time per iteration (s): 0.22 | learning rate: 1.874E-04 | global batch size: 256 | lm loss: 3.137757E+00 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.251 | TFLOPs: 7.51 | +31: iteration 6480/ 37905 | consumed samples: 1658880 | consumed tokens: 3397386240 | elapsed time per iteration (s): 0.19 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.170039E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1348.813 | TFLOPs: 8.59 | +31: iteration 6490/ 37905 | consumed samples: 1661440 | consumed tokens: 3402629120 | elapsed time per iteration (s): 0.20 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.146789E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1309.105 | TFLOPs: 8.34 | +31: iteration 6500/ 37905 | consumed samples: 1664000 | consumed tokens: 3407872000 | elapsed time per iteration (s): 0.20 | learning rate: 1.873E-04 | global batch size: 256 | lm loss: 3.123614E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.887 | TFLOPs: 8.16 | +31: iteration 6510/ 37905 | consumed samples: 1666560 | consumed tokens: 3413114880 | elapsed time per iteration (s): 0.21 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.161172E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.275 | TFLOPs: 7.70 | +31: iteration 6520/ 37905 | consumed samples: 1669120 | consumed tokens: 3418357760 | elapsed time per iteration (s): 0.21 | learning rate: 1.872E-04 | global batch size: 256 | lm loss: 3.170064E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.044 | TFLOPs: 7.89 | +31: iteration 6530/ 37905 | consumed samples: 1671680 | consumed tokens: 3423600640 | elapsed time per iteration (s): 0.19 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.129364E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.520 | TFLOPs: 8.40 | +31: iteration 6540/ 37905 | consumed samples: 1674240 | consumed tokens: 3428843520 | elapsed time per iteration (s): 0.24 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.137817E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.244 | TFLOPs: 6.93 | +31: iteration 6550/ 37905 | consumed samples: 1676800 | consumed tokens: 3434086400 | elapsed time per iteration (s): 0.21 | learning rate: 1.871E-04 | global batch size: 256 | lm loss: 3.169574E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.170 | TFLOPs: 7.80 | +31: iteration 6560/ 37905 | consumed samples: 1679360 | consumed tokens: 3439329280 | elapsed time per iteration (s): 0.19 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 3.152977E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.711 | TFLOPs: 8.46 | +31: iteration 6570/ 37905 | consumed samples: 1681920 | consumed tokens: 3444572160 | elapsed time per iteration (s): 0.19 | learning rate: 1.870E-04 | global batch size: 256 | lm loss: 3.152386E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1366.710 | TFLOPs: 8.70 | +31: iteration 6580/ 37905 | consumed samples: 1684480 | consumed tokens: 3449815040 | elapsed time per iteration (s): 0.19 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.165709E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1348.905 | TFLOPs: 8.59 | +31: iteration 6590/ 37905 | consumed samples: 1687040 | consumed tokens: 3455057920 | elapsed time per iteration (s): 0.20 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.155351E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.854 | TFLOPs: 7.97 | +31: iteration 6600/ 37905 | consumed samples: 1689600 | consumed tokens: 3460300800 | elapsed time per iteration (s): 0.20 | learning rate: 1.869E-04 | global batch size: 256 | lm loss: 3.150707E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.116 | TFLOPs: 8.19 | +31: iteration 6610/ 37905 | consumed samples: 1692160 | consumed tokens: 3465543680 | elapsed time per iteration (s): 0.20 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.158907E+00 | grad norm: 0.403 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1276.299 | TFLOPs: 8.13 | +31: iteration 6620/ 37905 | consumed samples: 1694720 | consumed tokens: 3470786560 | elapsed time per iteration (s): 0.19 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.126600E+00 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1331.875 | TFLOPs: 8.48 | +31: iteration 6630/ 37905 | consumed samples: 1697280 | consumed tokens: 3476029440 | elapsed time per iteration (s): 0.19 | learning rate: 1.868E-04 | global batch size: 256 | lm loss: 3.163428E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.074 | TFLOPs: 8.45 | +31: iteration 6640/ 37905 | consumed samples: 1699840 | consumed tokens: 3481272320 | elapsed time per iteration (s): 0.22 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.124906E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.346 | TFLOPs: 7.46 | +31: iteration 6650/ 37905 | consumed samples: 1702400 | consumed tokens: 3486515200 | elapsed time per iteration (s): 0.21 | learning rate: 1.867E-04 | global batch size: 256 | lm loss: 3.111501E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.884 | TFLOPs: 7.74 | +31: iteration 6660/ 37905 | consumed samples: 1704960 | consumed tokens: 3491758080 | elapsed time per iteration (s): 0.20 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.174352E+00 | grad norm: 0.364 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.713 | TFLOPs: 8.21 | +31: iteration 6670/ 37905 | consumed samples: 1707520 | consumed tokens: 3497000960 | elapsed time per iteration (s): 0.19 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.133292E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1348.635 | TFLOPs: 8.59 | +31: iteration 6680/ 37905 | consumed samples: 1710080 | consumed tokens: 3502243840 | elapsed time per iteration (s): 0.21 | learning rate: 1.866E-04 | global batch size: 256 | lm loss: 3.128633E+00 | grad norm: 0.371 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.778 | TFLOPs: 7.92 | +31: iteration 6690/ 37905 | consumed samples: 1712640 | consumed tokens: 3507486720 | elapsed time per iteration (s): 0.19 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.145179E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1336.112 | TFLOPs: 8.51 | +31: iteration 6700/ 37905 | consumed samples: 1715200 | consumed tokens: 3512729600 | elapsed time per iteration (s): 0.18 | learning rate: 1.865E-04 | global batch size: 256 | lm loss: 3.152116E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1414.460 | TFLOPs: 9.01 | +31: iteration 6710/ 37905 | consumed samples: 1717760 | consumed tokens: 3517972480 | elapsed time per iteration (s): 0.19 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.168392E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1355.378 | TFLOPs: 8.63 | +31: iteration 6720/ 37905 | consumed samples: 1720320 | consumed tokens: 3523215360 | elapsed time per iteration (s): 0.22 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.125090E+00 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.363 | TFLOPs: 7.40 | +31: iteration 6730/ 37905 | consumed samples: 1722880 | consumed tokens: 3528458240 | elapsed time per iteration (s): 0.21 | learning rate: 1.864E-04 | global batch size: 256 | lm loss: 3.170305E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1230.242 | TFLOPs: 7.84 | +31: iteration 6740/ 37905 | consumed samples: 1725440 | consumed tokens: 3533701120 | elapsed time per iteration (s): 0.20 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.147838E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.131 | TFLOPs: 8.01 | +31: iteration 6750/ 37905 | consumed samples: 1728000 | consumed tokens: 3538944000 | elapsed time per iteration (s): 0.18 | learning rate: 1.863E-04 | global batch size: 256 | lm loss: 3.125178E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1400.924 | TFLOPs: 8.92 | +31: iteration 6760/ 37905 | consumed samples: 1730560 | consumed tokens: 3544186880 | elapsed time per iteration (s): 0.20 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.143549E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.239 | TFLOPs: 8.00 | +31: iteration 6770/ 37905 | consumed samples: 1733120 | consumed tokens: 3549429760 | elapsed time per iteration (s): 0.18 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.101162E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1396.545 | TFLOPs: 8.89 | +31: iteration 6780/ 37905 | consumed samples: 1735680 | consumed tokens: 3554672640 | elapsed time per iteration (s): 0.22 | learning rate: 1.862E-04 | global batch size: 256 | lm loss: 3.114042E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.250 | TFLOPs: 7.45 | +31: iteration 6790/ 37905 | consumed samples: 1738240 | consumed tokens: 3559915520 | elapsed time per iteration (s): 0.21 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.144461E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.381 | TFLOPs: 7.74 | +31: iteration 6800/ 37905 | consumed samples: 1740800 | consumed tokens: 3565158400 | elapsed time per iteration (s): 0.18 | learning rate: 1.861E-04 | global batch size: 256 | lm loss: 3.194002E+00 | grad norm: 0.373 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1453.900 | TFLOPs: 9.26 | +31: iteration 6810/ 37905 | consumed samples: 1743360 | consumed tokens: 3570401280 | elapsed time per iteration (s): 0.21 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.131592E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.831 | TFLOPs: 7.80 | +31: iteration 6820/ 37905 | consumed samples: 1745920 | consumed tokens: 3575644160 | elapsed time per iteration (s): 0.22 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.134704E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.756 | TFLOPs: 7.56 | +31: iteration 6830/ 37905 | consumed samples: 1748480 | consumed tokens: 3580887040 | elapsed time per iteration (s): 0.21 | learning rate: 1.860E-04 | global batch size: 256 | lm loss: 3.152450E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.925 | TFLOPs: 7.88 | +31: iteration 6840/ 37905 | consumed samples: 1751040 | consumed tokens: 3586129920 | elapsed time per iteration (s): 0.21 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 3.140549E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.700 | TFLOPs: 7.79 | +31: iteration 6850/ 37905 | consumed samples: 1753600 | consumed tokens: 3591372800 | elapsed time per iteration (s): 0.20 | learning rate: 1.859E-04 | global batch size: 256 | lm loss: 3.141907E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.661 | TFLOPs: 7.98 | +31: iteration 6860/ 37905 | consumed samples: 1756160 | consumed tokens: 3596615680 | elapsed time per iteration (s): 0.19 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.116011E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1359.718 | TFLOPs: 8.66 | +31: iteration 6870/ 37905 | consumed samples: 1758720 | consumed tokens: 3601858560 | elapsed time per iteration (s): 0.22 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.172883E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.842 | TFLOPs: 7.35 | +31: iteration 6880/ 37905 | consumed samples: 1761280 | consumed tokens: 3607101440 | elapsed time per iteration (s): 0.18 | learning rate: 1.858E-04 | global batch size: 256 | lm loss: 3.157836E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1412.540 | TFLOPs: 9.00 | +31: iteration 6890/ 37905 | consumed samples: 1763840 | consumed tokens: 3612344320 | elapsed time per iteration (s): 0.19 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.089206E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.121 | TFLOPs: 8.45 | +31: iteration 6900/ 37905 | consumed samples: 1766400 | consumed tokens: 3617587200 | elapsed time per iteration (s): 0.19 | learning rate: 1.857E-04 | global batch size: 256 | lm loss: 3.092138E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1372.373 | TFLOPs: 8.74 | +31: iteration 6910/ 37905 | consumed samples: 1768960 | consumed tokens: 3622830080 | elapsed time per iteration (s): 0.20 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.136289E+00 | grad norm: 0.370 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.690 | TFLOPs: 8.14 | +31: iteration 6920/ 37905 | consumed samples: 1771520 | consumed tokens: 3628072960 | elapsed time per iteration (s): 0.19 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.130975E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1361.236 | TFLOPs: 8.67 | +31: iteration 6930/ 37905 | consumed samples: 1774080 | consumed tokens: 3633315840 | elapsed time per iteration (s): 0.22 | learning rate: 1.856E-04 | global batch size: 256 | lm loss: 3.122119E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.240 | TFLOPs: 7.50 | +31: iteration 6940/ 37905 | consumed samples: 1776640 | consumed tokens: 3638558720 | elapsed time per iteration (s): 0.21 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.149164E+00 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.765 | TFLOPs: 7.79 | +31: iteration 6950/ 37905 | consumed samples: 1779200 | consumed tokens: 3643801600 | elapsed time per iteration (s): 0.21 | learning rate: 1.855E-04 | global batch size: 256 | lm loss: 3.124469E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1248.688 | TFLOPs: 7.95 | +31: iteration 6960/ 37905 | consumed samples: 1781760 | consumed tokens: 3649044480 | elapsed time per iteration (s): 0.20 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.173501E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.185 | TFLOPs: 8.21 | +31: iteration 6970/ 37905 | consumed samples: 1784320 | consumed tokens: 3654287360 | elapsed time per iteration (s): 0.19 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.115741E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.835 | TFLOPs: 8.45 | +31: iteration 6980/ 37905 | consumed samples: 1786880 | consumed tokens: 3659530240 | elapsed time per iteration (s): 0.19 | learning rate: 1.854E-04 | global batch size: 256 | lm loss: 3.099566E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.287 | TFLOPs: 8.78 | +31: iteration 6990/ 37905 | consumed samples: 1789440 | consumed tokens: 3664773120 | elapsed time per iteration (s): 0.18 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 3.161258E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1404.040 | TFLOPs: 8.94 | +31: iteration 7000/ 37905 | consumed samples: 1792000 | consumed tokens: 3670016000 | elapsed time per iteration (s): 0.24 | learning rate: 1.853E-04 | global batch size: 256 | lm loss: 3.148045E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.575 | TFLOPs: 6.71 | +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 7000 | lm loss value: 3.082338E+00 | lm loss PPL: 2.180933E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 7000 to checkpoints_83m + 0: [2022-11-24 14:37:27,846] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step7000 is begin to save! + 0: [2022-11-24 14:37:27,854] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:37:27,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:37:27,930] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:37:27,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:37:27,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:37:27,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:37:27,954] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:37:27,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:37:27,965] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:37:27,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:37:27,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:37:27,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:37:27,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:37:27,998] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:37:27,998] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:37:28,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:37:28,009] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:37:28,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:37:28,020] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:37:28,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:37:28,031] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:37:28,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:37:28,042] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:37:28,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:37:28,044] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step7000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:37:28,044] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:37:28,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step7000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:37:28,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:37:28,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +28: [2022-11-24 14:37:28,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:37:28,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:37:28,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 7: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 7: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +17: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 2: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +28: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +11: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:37:28,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 5: [2022-11-24 14:37:28,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:37:28,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:37:28,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:37:28,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +20: [2022-11-24 14:37:28,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:37:28,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 2: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +23: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +11: [2022-11-24 14:37:28,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +28: [2022-11-24 14:37:28,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 7: [2022-11-24 14:37:28,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:37:28,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:37:28,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:37:28,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:37:28,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:37:28,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:37:28,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:37:28,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:37:28,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 2: [2022-11-24 14:37:28,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:37:28,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +24: [2022-11-24 14:37:28,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +23: [2022-11-24 14:37:28,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +11: [2022-11-24 14:37:28,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +29: [2022-11-24 14:37:28,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +27: [2022-11-24 14:37:28,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +16: [2022-11-24 14:37:28,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +22: [2022-11-24 14:37:28,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +14: [2022-11-24 14:37:28,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +20: [2022-11-24 14:37:28,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 7: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +17: [2022-11-24 14:37:28,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +11: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 5: [2022-11-24 14:37:28,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +28: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:37:28,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:37:28,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +24: [2022-11-24 14:37:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +23: [2022-11-24 14:37:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +11: [2022-11-24 14:37:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +29: [2022-11-24 14:37:28,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +27: [2022-11-24 14:37:28,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +16: [2022-11-24 14:37:28,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +22: [2022-11-24 14:37:28,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 2: [2022-11-24 14:37:28,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +14: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +20: [2022-11-24 14:37:28,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 7: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +17: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +11: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 5: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +28: [2022-11-24 14:37:28,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:37:28,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:37:28,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:37:28,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:37:28,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:37:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:37:28,153] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +23: [2022-11-24 14:37:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,153] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +11: [2022-11-24 14:37:28,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +27: [2022-11-24 14:37:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +16: [2022-11-24 14:37:28,153] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +22: [2022-11-24 14:37:28,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:37:28,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 2: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +14: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +20: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +24: [2022-11-24 14:37:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 7: [2022-11-24 14:37:28,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +17: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +11: [2022-11-24 14:37:28,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 5: [2022-11-24 14:37:28,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +28: [2022-11-24 14:37:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +24: [2022-11-24 14:37:28,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:37:28,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:37:28,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:37:28,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +14: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +20: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:37:28,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:37:28,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +17: [2022-11-24 14:37:28,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 2: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +28: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +23: [2022-11-24 14:37:28,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +12: [2022-11-24 14:37:28,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +11: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:37:28,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 7: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:37:28,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +29: [2022-11-24 14:37:28,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:37:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:37:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +29: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:37:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 5: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +18: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +22: [2022-11-24 14:37:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +16: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +22: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +14: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +20: [2022-11-24 14:37:28,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:37:28,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +14: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +28: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 3: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +15: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +12: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +22: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 6: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +10: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +15: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +17: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +29: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +20: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +17: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +29: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +27: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +10: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +30: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +16: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 2: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 4: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +11: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +25: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +30: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +16: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 8: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +11: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 9: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +31: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +26: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +23: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +31: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +14: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +24: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 5: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +25: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +19: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:37:28,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +26: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +23: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 5: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +27: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 1: [2022-11-24 14:37:28,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +14: [2022-11-24 14:37:28,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +21: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:37:28,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +24: [2022-11-24 14:37:28,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +18: [2022-11-24 14:37:28,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! +13: [2022-11-24 14:37:28,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:37:28,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step7000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:37:28,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step7000 is ready now! + 0: successfully saved checkpoint at iteration 7000 to checkpoints_83m +31: time (ms) | save-checkpoint: 328.81 +31: iteration 7010/ 37905 | consumed samples: 1794560 | consumed tokens: 3675258880 | elapsed time per iteration (s): 0.24 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.119061E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.542 | TFLOPs: 6.79 | +31: iteration 7020/ 37905 | consumed samples: 1797120 | consumed tokens: 3680501760 | elapsed time per iteration (s): 0.19 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.180126E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.532 | TFLOPs: 8.44 | +31: iteration 7030/ 37905 | consumed samples: 1799680 | consumed tokens: 3685744640 | elapsed time per iteration (s): 0.19 | learning rate: 1.852E-04 | global batch size: 256 | lm loss: 3.110763E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1381.398 | TFLOPs: 8.80 | +31: iteration 7040/ 37905 | consumed samples: 1802240 | consumed tokens: 3690987520 | elapsed time per iteration (s): 0.21 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.155285E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.623 | TFLOPs: 7.91 | +31: iteration 7050/ 37905 | consumed samples: 1804800 | consumed tokens: 3696230400 | elapsed time per iteration (s): 0.21 | learning rate: 1.851E-04 | global batch size: 256 | lm loss: 3.152464E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.888 | TFLOPs: 7.78 | +31: iteration 7060/ 37905 | consumed samples: 1807360 | consumed tokens: 3701473280 | elapsed time per iteration (s): 0.18 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.118917E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1394.935 | TFLOPs: 8.88 | +31: iteration 7070/ 37905 | consumed samples: 1809920 | consumed tokens: 3706716160 | elapsed time per iteration (s): 0.20 | learning rate: 1.850E-04 | global batch size: 256 | lm loss: 3.138141E+00 | grad norm: 0.388 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.235 | TFLOPs: 8.16 | +31: iteration 7080/ 37905 | consumed samples: 1812480 | consumed tokens: 3711959040 | elapsed time per iteration (s): 0.20 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.119706E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.067 | TFLOPs: 8.32 | +31: iteration 7090/ 37905 | consumed samples: 1815040 | consumed tokens: 3717201920 | elapsed time per iteration (s): 0.20 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.143205E+00 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.989 | TFLOPs: 8.07 | +31: iteration 7100/ 37905 | consumed samples: 1817600 | consumed tokens: 3722444800 | elapsed time per iteration (s): 0.20 | learning rate: 1.849E-04 | global batch size: 256 | lm loss: 3.104942E+00 | grad norm: 0.382 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.589 | TFLOPs: 8.14 | +31: iteration 7110/ 37905 | consumed samples: 1820160 | consumed tokens: 3727687680 | elapsed time per iteration (s): 0.20 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.165098E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.509 | TFLOPs: 7.96 | +31: iteration 7120/ 37905 | consumed samples: 1822720 | consumed tokens: 3732930560 | elapsed time per iteration (s): 0.19 | learning rate: 1.848E-04 | global batch size: 256 | lm loss: 3.128200E+00 | grad norm: 0.454 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.105 | TFLOPs: 8.55 | +31: iteration 7130/ 37905 | consumed samples: 1825280 | consumed tokens: 3738173440 | elapsed time per iteration (s): 0.20 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.151168E+00 | grad norm: 0.387 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.578 | TFLOPs: 8.35 | +31: iteration 7140/ 37905 | consumed samples: 1827840 | consumed tokens: 3743416320 | elapsed time per iteration (s): 0.19 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.128538E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.994 | TFLOPs: 8.55 | +31: iteration 7150/ 37905 | consumed samples: 1830400 | consumed tokens: 3748659200 | elapsed time per iteration (s): 0.20 | learning rate: 1.847E-04 | global batch size: 256 | lm loss: 3.135949E+00 | grad norm: 0.438 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.889 | TFLOPs: 8.14 | +31: iteration 7160/ 37905 | consumed samples: 1832960 | consumed tokens: 3753902080 | elapsed time per iteration (s): 0.19 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.161908E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1376.044 | TFLOPs: 8.76 | +31: iteration 7170/ 37905 | consumed samples: 1835520 | consumed tokens: 3759144960 | elapsed time per iteration (s): 0.19 | learning rate: 1.846E-04 | global batch size: 256 | lm loss: 3.163443E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1369.463 | TFLOPs: 8.72 | +31: iteration 7180/ 37905 | consumed samples: 1838080 | consumed tokens: 3764387840 | elapsed time per iteration (s): 0.19 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.143913E+00 | grad norm: 0.460 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1314.879 | TFLOPs: 8.37 | +31: iteration 7190/ 37905 | consumed samples: 1840640 | consumed tokens: 3769630720 | elapsed time per iteration (s): 0.20 | learning rate: 1.845E-04 | global batch size: 256 | lm loss: 3.114752E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1310.936 | TFLOPs: 8.35 | +31: iteration 7200/ 37905 | consumed samples: 1843200 | consumed tokens: 3774873600 | elapsed time per iteration (s): 0.20 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.119949E+00 | grad norm: 0.396 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.748 | TFLOPs: 8.05 | +31: iteration 7210/ 37905 | consumed samples: 1845760 | consumed tokens: 3780116480 | elapsed time per iteration (s): 0.21 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.142499E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.435 | TFLOPs: 7.88 | +31: iteration 7220/ 37905 | consumed samples: 1848320 | consumed tokens: 3785359360 | elapsed time per iteration (s): 0.25 | learning rate: 1.844E-04 | global batch size: 256 | lm loss: 3.132682E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.892 | TFLOPs: 6.62 | +31: iteration 7230/ 37905 | consumed samples: 1850880 | consumed tokens: 3790602240 | elapsed time per iteration (s): 0.19 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.140479E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.625 | TFLOPs: 8.41 | +31: iteration 7240/ 37905 | consumed samples: 1853440 | consumed tokens: 3795845120 | elapsed time per iteration (s): 0.19 | learning rate: 1.843E-04 | global batch size: 256 | lm loss: 3.150962E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.031 | TFLOPs: 8.57 | +31: iteration 7250/ 37905 | consumed samples: 1856000 | consumed tokens: 3801088000 | elapsed time per iteration (s): 0.19 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.166585E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.394 | TFLOPs: 8.55 | +31: iteration 7260/ 37905 | consumed samples: 1858560 | consumed tokens: 3806330880 | elapsed time per iteration (s): 0.20 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.106368E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.689 | TFLOPs: 8.21 | +31: iteration 7270/ 37905 | consumed samples: 1861120 | consumed tokens: 3811573760 | elapsed time per iteration (s): 0.21 | learning rate: 1.842E-04 | global batch size: 256 | lm loss: 3.148857E+00 | grad norm: 0.486 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.112 | TFLOPs: 7.75 | +31: iteration 7280/ 37905 | consumed samples: 1863680 | consumed tokens: 3816816640 | elapsed time per iteration (s): 0.21 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 3.158939E+00 | grad norm: 0.412 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.996 | TFLOPs: 7.79 | +31: iteration 7290/ 37905 | consumed samples: 1866240 | consumed tokens: 3822059520 | elapsed time per iteration (s): 0.21 | learning rate: 1.841E-04 | global batch size: 256 | lm loss: 3.144521E+00 | grad norm: 0.391 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.877 | TFLOPs: 7.81 | +31: iteration 7300/ 37905 | consumed samples: 1868800 | consumed tokens: 3827302400 | elapsed time per iteration (s): 0.21 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.154781E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.604 | TFLOPs: 7.68 | +31: iteration 7310/ 37905 | consumed samples: 1871360 | consumed tokens: 3832545280 | elapsed time per iteration (s): 0.18 | learning rate: 1.840E-04 | global batch size: 256 | lm loss: 3.136898E+00 | grad norm: 0.443 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1401.221 | TFLOPs: 8.92 | +31: iteration 7320/ 37905 | consumed samples: 1873920 | consumed tokens: 3837788160 | elapsed time per iteration (s): 0.21 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.124857E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.759 | TFLOPs: 7.95 | +31: iteration 7330/ 37905 | consumed samples: 1876480 | consumed tokens: 3843031040 | elapsed time per iteration (s): 0.21 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.144441E+00 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.092 | TFLOPs: 7.66 | +31: iteration 7340/ 37905 | consumed samples: 1879040 | consumed tokens: 3848273920 | elapsed time per iteration (s): 0.21 | learning rate: 1.839E-04 | global batch size: 256 | lm loss: 3.107653E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.902 | TFLOPs: 7.68 | +31: iteration 7350/ 37905 | consumed samples: 1881600 | consumed tokens: 3853516800 | elapsed time per iteration (s): 0.19 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.123138E+00 | grad norm: 0.427 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.321 | TFLOPs: 8.41 | +31: iteration 7360/ 37905 | consumed samples: 1884160 | consumed tokens: 3858759680 | elapsed time per iteration (s): 0.21 | learning rate: 1.838E-04 | global batch size: 256 | lm loss: 3.147558E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.588 | TFLOPs: 7.90 | +31: iteration 7370/ 37905 | consumed samples: 1886720 | consumed tokens: 3864002560 | elapsed time per iteration (s): 0.21 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.126237E+00 | grad norm: 0.405 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.956 | TFLOPs: 7.87 | +31: iteration 7380/ 37905 | consumed samples: 1889280 | consumed tokens: 3869245440 | elapsed time per iteration (s): 0.18 | learning rate: 1.837E-04 | global batch size: 256 | lm loss: 3.130906E+00 | grad norm: 0.409 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1416.842 | TFLOPs: 9.02 | +31: iteration 7390/ 37905 | consumed samples: 1891840 | consumed tokens: 3874488320 | elapsed time per iteration (s): 0.21 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.095110E+00 | grad norm: 0.358 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.691 | TFLOPs: 7.61 | +31: iteration 7400/ 37905 | consumed samples: 1894400 | consumed tokens: 3879731200 | elapsed time per iteration (s): 0.21 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.138083E+00 | grad norm: 0.367 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.839 | TFLOPs: 7.85 | +31: iteration 7410/ 37905 | consumed samples: 1896960 | consumed tokens: 3884974080 | elapsed time per iteration (s): 0.19 | learning rate: 1.836E-04 | global batch size: 256 | lm loss: 3.147593E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.425 | TFLOPs: 8.52 | +31: iteration 7420/ 37905 | consumed samples: 1899520 | consumed tokens: 3890216960 | elapsed time per iteration (s): 0.20 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.094302E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.636 | TFLOPs: 8.21 | +31: iteration 7430/ 37905 | consumed samples: 1902080 | consumed tokens: 3895459840 | elapsed time per iteration (s): 0.21 | learning rate: 1.835E-04 | global batch size: 256 | lm loss: 3.127703E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.832 | TFLOPs: 7.69 | +31: iteration 7440/ 37905 | consumed samples: 1904640 | consumed tokens: 3900702720 | elapsed time per iteration (s): 0.22 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 3.074955E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.761 | TFLOPs: 7.44 | +31: iteration 7450/ 37905 | consumed samples: 1907200 | consumed tokens: 3905945600 | elapsed time per iteration (s): 0.18 | learning rate: 1.834E-04 | global batch size: 256 | lm loss: 3.127000E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1453.889 | TFLOPs: 9.26 | +31: iteration 7460/ 37905 | consumed samples: 1909760 | consumed tokens: 3911188480 | elapsed time per iteration (s): 0.17 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.139380E+00 | grad norm: 0.418 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1479.744 | TFLOPs: 9.42 | +31: iteration 7470/ 37905 | consumed samples: 1912320 | consumed tokens: 3916431360 | elapsed time per iteration (s): 0.22 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.097072E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.300 | TFLOPs: 7.47 | +31: iteration 7480/ 37905 | consumed samples: 1914880 | consumed tokens: 3921674240 | elapsed time per iteration (s): 0.19 | learning rate: 1.833E-04 | global batch size: 256 | lm loss: 3.100364E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1351.637 | TFLOPs: 8.61 | +31: iteration 7490/ 37905 | consumed samples: 1917440 | consumed tokens: 3926917120 | elapsed time per iteration (s): 0.23 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.132726E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1136.517 | TFLOPs: 7.24 | +31: iteration 7500/ 37905 | consumed samples: 1920000 | consumed tokens: 3932160000 | elapsed time per iteration (s): 0.21 | learning rate: 1.832E-04 | global batch size: 256 | lm loss: 3.090869E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.220 | TFLOPs: 7.61 | +31: iteration 7510/ 37905 | consumed samples: 1922560 | consumed tokens: 3937402880 | elapsed time per iteration (s): 0.21 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.098508E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.564 | TFLOPs: 7.69 | +31: iteration 7520/ 37905 | consumed samples: 1925120 | consumed tokens: 3942645760 | elapsed time per iteration (s): 0.19 | learning rate: 1.831E-04 | global batch size: 256 | lm loss: 3.148641E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1356.107 | TFLOPs: 8.64 | +31: iteration 7530/ 37905 | consumed samples: 1927680 | consumed tokens: 3947888640 | elapsed time per iteration (s): 0.19 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 3.153008E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.633 | TFLOPs: 8.58 | +31: iteration 7540/ 37905 | consumed samples: 1930240 | consumed tokens: 3953131520 | elapsed time per iteration (s): 0.19 | learning rate: 1.830E-04 | global batch size: 256 | lm loss: 3.135787E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1381.922 | TFLOPs: 8.80 | +31: iteration 7550/ 37905 | consumed samples: 1932800 | consumed tokens: 3958374400 | elapsed time per iteration (s): 0.18 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.105984E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1394.160 | TFLOPs: 8.88 | +31: iteration 7560/ 37905 | consumed samples: 1935360 | consumed tokens: 3963617280 | elapsed time per iteration (s): 0.21 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.106752E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.944 | TFLOPs: 7.79 | +31: iteration 7570/ 37905 | consumed samples: 1937920 | consumed tokens: 3968860160 | elapsed time per iteration (s): 0.19 | learning rate: 1.829E-04 | global batch size: 256 | lm loss: 3.125945E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.438 | TFLOPs: 8.56 | +31: iteration 7580/ 37905 | consumed samples: 1940480 | consumed tokens: 3974103040 | elapsed time per iteration (s): 0.21 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 3.144972E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.487 | TFLOPs: 7.79 | +31: iteration 7590/ 37905 | consumed samples: 1943040 | consumed tokens: 3979345920 | elapsed time per iteration (s): 0.21 | learning rate: 1.828E-04 | global batch size: 256 | lm loss: 3.147712E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.930 | TFLOPs: 7.83 | +31: iteration 7600/ 37905 | consumed samples: 1945600 | consumed tokens: 3984588800 | elapsed time per iteration (s): 0.19 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.112292E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.331 | TFLOPs: 8.39 | +31: iteration 7610/ 37905 | consumed samples: 1948160 | consumed tokens: 3989831680 | elapsed time per iteration (s): 0.20 | learning rate: 1.827E-04 | global batch size: 256 | lm loss: 3.163683E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.194 | TFLOPs: 7.99 | +31: iteration 7620/ 37905 | consumed samples: 1950720 | consumed tokens: 3995074560 | elapsed time per iteration (s): 0.19 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.076293E+00 | grad norm: 0.395 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.885 | TFLOPs: 8.54 | +31: iteration 7630/ 37905 | consumed samples: 1953280 | consumed tokens: 4000317440 | elapsed time per iteration (s): 0.18 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.100676E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1387.834 | TFLOPs: 8.84 | +31: iteration 7640/ 37905 | consumed samples: 1955840 | consumed tokens: 4005560320 | elapsed time per iteration (s): 0.19 | learning rate: 1.826E-04 | global batch size: 256 | lm loss: 3.136977E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1372.009 | TFLOPs: 8.74 | +31: iteration 7650/ 37905 | consumed samples: 1958400 | consumed tokens: 4010803200 | elapsed time per iteration (s): 0.18 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 3.125347E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1434.066 | TFLOPs: 9.13 | +31: iteration 7660/ 37905 | consumed samples: 1960960 | consumed tokens: 4016046080 | elapsed time per iteration (s): 0.19 | learning rate: 1.825E-04 | global batch size: 256 | lm loss: 3.083195E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1371.563 | TFLOPs: 8.74 | +31: iteration 7670/ 37905 | consumed samples: 1963520 | consumed tokens: 4021288960 | elapsed time per iteration (s): 0.20 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.116214E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.128 | TFLOPs: 8.22 | +31: iteration 7680/ 37905 | consumed samples: 1966080 | consumed tokens: 4026531840 | elapsed time per iteration (s): 0.19 | learning rate: 1.824E-04 | global batch size: 256 | lm loss: 3.098796E+00 | grad norm: 0.386 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.148 | TFLOPs: 8.57 | +31: iteration 7690/ 37905 | consumed samples: 1968640 | consumed tokens: 4031774720 | elapsed time per iteration (s): 0.20 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.139213E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.466 | TFLOPs: 8.07 | +31: iteration 7700/ 37905 | consumed samples: 1971200 | consumed tokens: 4037017600 | elapsed time per iteration (s): 0.21 | learning rate: 1.823E-04 | global batch size: 256 | lm loss: 3.112587E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.179 | TFLOPs: 7.84 | +31: iteration 7710/ 37905 | consumed samples: 1973760 | consumed tokens: 4042260480 | elapsed time per iteration (s): 0.24 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.111569E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.741 | TFLOPs: 6.67 | +31: iteration 7720/ 37905 | consumed samples: 1976320 | consumed tokens: 4047503360 | elapsed time per iteration (s): 0.20 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.119165E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.796 | TFLOPs: 8.16 | +31: iteration 7730/ 37905 | consumed samples: 1978880 | consumed tokens: 4052746240 | elapsed time per iteration (s): 0.20 | learning rate: 1.822E-04 | global batch size: 256 | lm loss: 3.145998E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.962 | TFLOPs: 8.25 | +31: iteration 7740/ 37905 | consumed samples: 1981440 | consumed tokens: 4057989120 | elapsed time per iteration (s): 0.22 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 3.121510E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.529 | TFLOPs: 7.51 | +31: iteration 7750/ 37905 | consumed samples: 1984000 | consumed tokens: 4063232000 | elapsed time per iteration (s): 0.21 | learning rate: 1.821E-04 | global batch size: 256 | lm loss: 3.124695E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.260 | TFLOPs: 7.74 | +31: iteration 7760/ 37905 | consumed samples: 1986560 | consumed tokens: 4068474880 | elapsed time per iteration (s): 0.21 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.127962E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.118 | TFLOPs: 7.80 | +31: iteration 7770/ 37905 | consumed samples: 1989120 | consumed tokens: 4073717760 | elapsed time per iteration (s): 0.19 | learning rate: 1.820E-04 | global batch size: 256 | lm loss: 3.114185E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1372.854 | TFLOPs: 8.74 | +31: iteration 7780/ 37905 | consumed samples: 1991680 | consumed tokens: 4078960640 | elapsed time per iteration (s): 0.19 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.164728E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1373.965 | TFLOPs: 8.75 | +31: iteration 7790/ 37905 | consumed samples: 1994240 | consumed tokens: 4084203520 | elapsed time per iteration (s): 0.22 | learning rate: 1.819E-04 | global batch size: 256 | lm loss: 3.106777E+00 | grad norm: 0.421 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.975 | TFLOPs: 7.37 | +31: iteration 7800/ 37905 | consumed samples: 1996800 | consumed tokens: 4089446400 | elapsed time per iteration (s): 0.19 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 3.113944E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1318.687 | TFLOPs: 8.40 | +31: iteration 7810/ 37905 | consumed samples: 1999360 | consumed tokens: 4094689280 | elapsed time per iteration (s): 0.20 | learning rate: 1.818E-04 | global batch size: 256 | lm loss: 3.099634E+00 | grad norm: 0.398 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.554 | TFLOPs: 8.26 | +31: iteration 7820/ 37905 | consumed samples: 2001920 | consumed tokens: 4099932160 | elapsed time per iteration (s): 0.19 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.161392E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.793 | TFLOPs: 8.39 | +31: iteration 7830/ 37905 | consumed samples: 2004480 | consumed tokens: 4105175040 | elapsed time per iteration (s): 0.21 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.103529E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.368 | TFLOPs: 7.94 | +31: iteration 7840/ 37905 | consumed samples: 2007040 | consumed tokens: 4110417920 | elapsed time per iteration (s): 0.18 | learning rate: 1.817E-04 | global batch size: 256 | lm loss: 3.101724E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1435.300 | TFLOPs: 9.14 | +31: iteration 7850/ 37905 | consumed samples: 2009600 | consumed tokens: 4115660800 | elapsed time per iteration (s): 0.19 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.148897E+00 | grad norm: 0.385 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.165 | TFLOPs: 8.78 | +31: iteration 7860/ 37905 | consumed samples: 2012160 | consumed tokens: 4120903680 | elapsed time per iteration (s): 0.19 | learning rate: 1.816E-04 | global batch size: 256 | lm loss: 3.101989E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.271 | TFLOPs: 8.54 | +31: iteration 7870/ 37905 | consumed samples: 2014720 | consumed tokens: 4126146560 | elapsed time per iteration (s): 0.21 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.132600E+00 | grad norm: 0.402 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.695 | TFLOPs: 7.86 | +31: iteration 7880/ 37905 | consumed samples: 2017280 | consumed tokens: 4131389440 | elapsed time per iteration (s): 0.20 | learning rate: 1.815E-04 | global batch size: 256 | lm loss: 3.105633E+00 | grad norm: 0.368 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.893 | TFLOPs: 8.36 | +31: iteration 7890/ 37905 | consumed samples: 2019840 | consumed tokens: 4136632320 | elapsed time per iteration (s): 0.18 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 3.108695E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1441.703 | TFLOPs: 9.18 | +31: iteration 7900/ 37905 | consumed samples: 2022400 | consumed tokens: 4141875200 | elapsed time per iteration (s): 0.24 | learning rate: 1.814E-04 | global batch size: 256 | lm loss: 3.083358E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.118 | TFLOPs: 6.83 | +31: iteration 7910/ 37905 | consumed samples: 2024960 | consumed tokens: 4147118080 | elapsed time per iteration (s): 0.18 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.137801E+00 | grad norm: 0.410 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1438.683 | TFLOPs: 9.16 | +31: iteration 7920/ 37905 | consumed samples: 2027520 | consumed tokens: 4152360960 | elapsed time per iteration (s): 0.20 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.095660E+00 | grad norm: 0.356 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.887 | TFLOPs: 8.18 | +31: iteration 7930/ 37905 | consumed samples: 2030080 | consumed tokens: 4157603840 | elapsed time per iteration (s): 0.21 | learning rate: 1.813E-04 | global batch size: 256 | lm loss: 3.147795E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.940 | TFLOPs: 7.87 | +31: iteration 7940/ 37905 | consumed samples: 2032640 | consumed tokens: 4162846720 | elapsed time per iteration (s): 0.20 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.079938E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.634 | TFLOPs: 7.97 | +31: iteration 7950/ 37905 | consumed samples: 2035200 | consumed tokens: 4168089600 | elapsed time per iteration (s): 0.21 | learning rate: 1.812E-04 | global batch size: 256 | lm loss: 3.083965E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.148 | TFLOPs: 7.90 | +31: iteration 7960/ 37905 | consumed samples: 2037760 | consumed tokens: 4173332480 | elapsed time per iteration (s): 0.20 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 3.164702E+00 | grad norm: 0.394 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.444 | TFLOPs: 8.09 | +31: iteration 7970/ 37905 | consumed samples: 2040320 | consumed tokens: 4178575360 | elapsed time per iteration (s): 0.19 | learning rate: 1.811E-04 | global batch size: 256 | lm loss: 3.121328E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.501 | TFLOPs: 8.38 | +31: iteration 7980/ 37905 | consumed samples: 2042880 | consumed tokens: 4183818240 | elapsed time per iteration (s): 0.22 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.115772E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.987 | TFLOPs: 7.50 | +31: iteration 7990/ 37905 | consumed samples: 2045440 | consumed tokens: 4189061120 | elapsed time per iteration (s): 0.19 | learning rate: 1.810E-04 | global batch size: 256 | lm loss: 3.156973E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1362.817 | TFLOPs: 8.68 | + 0: [2022-11-24 14:40:47,869] [INFO] [logging.py:68:log_dist] [Rank 0] step=8000, skipped=0, lr=[0.00018093099632815484, 0.00018093099632815484, 0.00018093099632815484], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 8000/ 37905 | consumed samples: 2048000 | consumed tokens: 4194304000 | elapsed time per iteration (s): 0.20 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.112971E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.728 | TFLOPs: 8.02 | + 0: steps: 8000 loss: 3.1012 iter time (s): 0.197 samples/sec: 1298.143 +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 8000 | lm loss value: 3.037055E+00 | lm loss PPL: 2.084377E+01 | +31: ------------------------------------------------------------------------------------------ + 0: saving checkpoint at iteration 8000 to checkpoints_83m + 0: [2022-11-24 14:40:47,955] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step8000 is begin to save! + 0: [2022-11-24 14:40:47,968] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,041] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,053] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,064] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,075] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,086] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,108] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,130] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,152] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:40:48,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:40:48,154] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step8000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:40:48,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:40:48,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:40:48,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step8000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:40:48,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:40:48,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:40:48,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 4: [2022-11-24 14:40:48,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 5: [2022-11-24 14:40:48,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 9: [2022-11-24 14:40:48,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:40:48,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 1: [2022-11-24 14:40:48,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:40:48,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:40:48,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +19: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +14: [2022-11-24 14:40:48,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +16: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +21: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +29: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:40:48,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:40:48,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +10: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +10: [2022-11-24 14:40:48,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:40:48,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:40:48,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 4: [2022-11-24 14:40:48,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 9: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:40:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 3: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +22: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:40:48,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 1: [2022-11-24 14:40:48,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:40:48,235] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:40:48,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:40:48,236] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,236] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:40:48,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +31: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,237] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,237] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +21: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 5: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +29: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:40:48,238] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:40:48,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,239] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:40:48,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 4: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:40:48,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 9: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:40:48,240] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +22: [2022-11-24 14:40:48,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 1: [2022-11-24 14:40:48,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:40:48,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,241] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:40:48,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,242] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:40:48,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,242] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:40:48,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +16: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +19: [2022-11-24 14:40:48,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,243] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:40:48,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +31: [2022-11-24 14:40:48,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,244] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,244] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +23: [2022-11-24 14:40:48,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 5: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,245] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:40:48,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +29: [2022-11-24 14:40:48,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:40:48,246] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,246] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +10: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:40:48,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 4: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:40:48,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 9: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,247] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:40:48,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,248] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,248] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +22: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:40:48,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:40:48,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 1: [2022-11-24 14:40:48,249] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:40:48,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 3: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:40:48,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +19: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,250] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +31: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +16: [2022-11-24 14:40:48,251] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:40:48,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:40:48,252] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,252] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,252] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,252] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +21: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,252] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,252] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:40:48,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +29: [2022-11-24 14:40:48,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,253] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:40:48,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +10: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:40:48,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 4: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:40:48,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 9: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:40:48,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:40:48,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +22: [2022-11-24 14:40:48,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 1: [2022-11-24 14:40:48,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:40:48,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:40:48,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +30: [2022-11-24 14:40:48,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:40:48,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +16: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +19: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:40:48,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 5: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +21: [2022-11-24 14:40:48,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:40:48,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +29: [2022-11-24 14:40:48,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:40:48,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:40:48,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +10: [2022-11-24 14:40:48,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:40:48,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:40:48,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:40:48,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:40:48,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 9: [2022-11-24 14:40:48,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:40:48,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 1: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +22: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 3: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:40:48,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:40:48,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +19: [2022-11-24 14:40:48,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +16: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +31: [2022-11-24 14:40:48,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:40:48,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:40:48,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 5: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +21: [2022-11-24 14:40:48,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +26: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:40:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +29: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:40:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +10: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:40:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:40:48,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 4: [2022-11-24 14:40:48,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:40:48,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:40:48,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 9: [2022-11-24 14:40:48,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:40:48,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 1: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +22: [2022-11-24 14:40:48,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:40:48,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:40:48,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 3: [2022-11-24 14:40:48,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:40:48,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:40:48,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +19: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +16: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +23: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 8: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +24: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +14: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +26: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +23: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +23: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +30: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +16: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +16: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +15: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +10: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 3: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 4: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +15: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +21: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +16: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +21: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 7: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +31: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +28: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +16: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 3: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +20: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +12: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +29: [2022-11-24 14:40:48,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +10: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +19: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 2: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 6: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +20: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:40:48,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +27: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +30: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +18: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +17: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +11: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +29: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +28: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +27: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +30: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +18: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +12: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +31: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +17: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +11: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +31: [2022-11-24 14:40:48,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 14:40:48,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +22: [2022-11-24 14:40:48,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:40:48,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:40:48,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:40:48,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +13: [2022-11-24 14:40:48,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:40:48,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! +25: [2022-11-24 14:40:48,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:40:48,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step8000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:40:48,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step8000 is ready now! + 0: successfully saved checkpoint at iteration 8000 to checkpoints_83m +31: time (ms) | save-checkpoint: 324.77 +31: iteration 8010/ 37905 | consumed samples: 2050560 | consumed tokens: 4199546880 | elapsed time per iteration (s): 0.22 | learning rate: 1.809E-04 | global batch size: 256 | lm loss: 3.146713E+00 | grad norm: 0.441 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.156 | TFLOPs: 7.58 | +31: iteration 8020/ 37905 | consumed samples: 2053120 | consumed tokens: 4204789760 | elapsed time per iteration (s): 0.19 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.104948E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1337.145 | TFLOPs: 8.52 | +31: iteration 8030/ 37905 | consumed samples: 2055680 | consumed tokens: 4210032640 | elapsed time per iteration (s): 0.18 | learning rate: 1.808E-04 | global batch size: 256 | lm loss: 3.089602E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1454.564 | TFLOPs: 9.26 | +31: iteration 8040/ 37905 | consumed samples: 2058240 | consumed tokens: 4215275520 | elapsed time per iteration (s): 0.19 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 3.096152E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1339.962 | TFLOPs: 8.53 | +31: iteration 8050/ 37905 | consumed samples: 2060800 | consumed tokens: 4220518400 | elapsed time per iteration (s): 0.20 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 3.091918E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.426 | TFLOPs: 8.17 | +31: iteration 8060/ 37905 | consumed samples: 2063360 | consumed tokens: 4225761280 | elapsed time per iteration (s): 0.19 | learning rate: 1.807E-04 | global batch size: 256 | lm loss: 3.144872E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.683 | TFLOPs: 8.41 | +31: iteration 8070/ 37905 | consumed samples: 2065920 | consumed tokens: 4231004160 | elapsed time per iteration (s): 0.19 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.096054E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.200 | TFLOPs: 8.38 | +31: iteration 8080/ 37905 | consumed samples: 2068480 | consumed tokens: 4236247040 | elapsed time per iteration (s): 0.18 | learning rate: 1.806E-04 | global batch size: 256 | lm loss: 3.096472E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1445.497 | TFLOPs: 9.21 | +31: iteration 8090/ 37905 | consumed samples: 2071040 | consumed tokens: 4241489920 | elapsed time per iteration (s): 0.18 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 3.087384E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1460.791 | TFLOPs: 9.30 | +31: iteration 8100/ 37905 | consumed samples: 2073600 | consumed tokens: 4246732800 | elapsed time per iteration (s): 0.19 | learning rate: 1.805E-04 | global batch size: 256 | lm loss: 3.112613E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.783 | TFLOPs: 8.46 | +31: iteration 8110/ 37905 | consumed samples: 2076160 | consumed tokens: 4251975680 | elapsed time per iteration (s): 0.18 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 3.090738E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1385.169 | TFLOPs: 8.82 | +31: iteration 8120/ 37905 | consumed samples: 2078720 | consumed tokens: 4257218560 | elapsed time per iteration (s): 0.19 | learning rate: 1.804E-04 | global batch size: 256 | lm loss: 3.098821E+00 | grad norm: 0.442 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.426 | TFLOPs: 8.54 | +31: iteration 8130/ 37905 | consumed samples: 2081280 | consumed tokens: 4262461440 | elapsed time per iteration (s): 0.20 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.090298E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.073 | TFLOPs: 8.24 | +31: iteration 8140/ 37905 | consumed samples: 2083840 | consumed tokens: 4267704320 | elapsed time per iteration (s): 0.19 | learning rate: 1.803E-04 | global batch size: 256 | lm loss: 3.110271E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.777 | TFLOPs: 8.55 | +31: iteration 8150/ 37905 | consumed samples: 2086400 | consumed tokens: 4272947200 | elapsed time per iteration (s): 0.21 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 3.088985E+00 | grad norm: 0.344 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1228.993 | TFLOPs: 7.83 | +31: iteration 8160/ 37905 | consumed samples: 2088960 | consumed tokens: 4278190080 | elapsed time per iteration (s): 0.20 | learning rate: 1.802E-04 | global batch size: 256 | lm loss: 3.120713E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1309.784 | TFLOPs: 8.34 | +31: iteration 8170/ 37905 | consumed samples: 2091520 | consumed tokens: 4283432960 | elapsed time per iteration (s): 0.21 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.099557E+00 | grad norm: 0.446 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.961 | TFLOPs: 7.66 | +31: iteration 8180/ 37905 | consumed samples: 2094080 | consumed tokens: 4288675840 | elapsed time per iteration (s): 0.19 | learning rate: 1.801E-04 | global batch size: 256 | lm loss: 3.088824E+00 | grad norm: 0.404 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.933 | TFLOPs: 8.36 | +31: iteration 8190/ 37905 | consumed samples: 2096640 | consumed tokens: 4293918720 | elapsed time per iteration (s): 0.20 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 3.130661E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.977 | TFLOPs: 8.05 | +31: iteration 8200/ 37905 | consumed samples: 2099200 | consumed tokens: 4299161600 | elapsed time per iteration (s): 0.21 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 3.163989E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.477 | TFLOPs: 7.79 | +31: iteration 8210/ 37905 | consumed samples: 2101760 | consumed tokens: 4304404480 | elapsed time per iteration (s): 0.18 | learning rate: 1.800E-04 | global batch size: 256 | lm loss: 3.122236E+00 | grad norm: 0.372 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1445.501 | TFLOPs: 9.21 | +31: iteration 8220/ 37905 | consumed samples: 2104320 | consumed tokens: 4309647360 | elapsed time per iteration (s): 0.19 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.107700E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1334.561 | TFLOPs: 8.50 | +31: iteration 8230/ 37905 | consumed samples: 2106880 | consumed tokens: 4314890240 | elapsed time per iteration (s): 0.22 | learning rate: 1.799E-04 | global batch size: 256 | lm loss: 3.071937E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.352 | TFLOPs: 7.42 | +31: iteration 8240/ 37905 | consumed samples: 2109440 | consumed tokens: 4320133120 | elapsed time per iteration (s): 0.20 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.105460E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1291.564 | TFLOPs: 8.23 | +31: iteration 8250/ 37905 | consumed samples: 2112000 | consumed tokens: 4325376000 | elapsed time per iteration (s): 0.19 | learning rate: 1.798E-04 | global batch size: 256 | lm loss: 3.138157E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1367.568 | TFLOPs: 8.71 | +31: iteration 8260/ 37905 | consumed samples: 2114560 | consumed tokens: 4330618880 | elapsed time per iteration (s): 0.19 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 3.116348E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1357.154 | TFLOPs: 8.64 | +31: iteration 8270/ 37905 | consumed samples: 2117120 | consumed tokens: 4335861760 | elapsed time per iteration (s): 0.19 | learning rate: 1.797E-04 | global batch size: 256 | lm loss: 3.108350E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.073 | TFLOPs: 8.53 | +31: iteration 8280/ 37905 | consumed samples: 2119680 | consumed tokens: 4341104640 | elapsed time per iteration (s): 0.18 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.096859E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.344 | TFLOPs: 8.93 | +31: iteration 8290/ 37905 | consumed samples: 2122240 | consumed tokens: 4346347520 | elapsed time per iteration (s): 0.19 | learning rate: 1.796E-04 | global batch size: 256 | lm loss: 3.152963E+00 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1318.708 | TFLOPs: 8.40 | +31: iteration 8300/ 37905 | consumed samples: 2124800 | consumed tokens: 4351590400 | elapsed time per iteration (s): 0.22 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.124333E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.126 | TFLOPs: 7.54 | +31: iteration 8310/ 37905 | consumed samples: 2127360 | consumed tokens: 4356833280 | elapsed time per iteration (s): 0.19 | learning rate: 1.795E-04 | global batch size: 256 | lm loss: 3.095512E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.798 | TFLOPs: 8.44 | +31: iteration 8320/ 37905 | consumed samples: 2129920 | consumed tokens: 4362076160 | elapsed time per iteration (s): 0.17 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 3.144299E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1463.526 | TFLOPs: 9.32 | +31: iteration 8330/ 37905 | consumed samples: 2132480 | consumed tokens: 4367319040 | elapsed time per iteration (s): 0.19 | learning rate: 1.794E-04 | global batch size: 256 | lm loss: 3.136598E+00 | grad norm: 0.349 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.625 | TFLOPs: 8.56 | +31: iteration 8340/ 37905 | consumed samples: 2135040 | consumed tokens: 4372561920 | elapsed time per iteration (s): 0.17 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.140432E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1475.239 | TFLOPs: 9.40 | +31: iteration 8350/ 37905 | consumed samples: 2137600 | consumed tokens: 4377804800 | elapsed time per iteration (s): 0.19 | learning rate: 1.793E-04 | global batch size: 256 | lm loss: 3.108949E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.685 | TFLOPs: 8.42 | +31: iteration 8360/ 37905 | consumed samples: 2140160 | consumed tokens: 4383047680 | elapsed time per iteration (s): 0.19 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 3.117128E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1329.879 | TFLOPs: 8.47 | +31: iteration 8370/ 37905 | consumed samples: 2142720 | consumed tokens: 4388290560 | elapsed time per iteration (s): 0.19 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 3.063125E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1336.318 | TFLOPs: 8.51 | +31: iteration 8380/ 37905 | consumed samples: 2145280 | consumed tokens: 4393533440 | elapsed time per iteration (s): 0.18 | learning rate: 1.792E-04 | global batch size: 256 | lm loss: 3.104694E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.678 | TFLOPs: 8.95 | +31: iteration 8390/ 37905 | consumed samples: 2147840 | consumed tokens: 4398776320 | elapsed time per iteration (s): 0.20 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.094196E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1276.137 | TFLOPs: 8.13 | +31: iteration 8400/ 37905 | consumed samples: 2150400 | consumed tokens: 4404019200 | elapsed time per iteration (s): 0.19 | learning rate: 1.791E-04 | global batch size: 256 | lm loss: 3.070654E+00 | grad norm: 0.384 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.636 | TFLOPs: 8.46 | +31: iteration 8410/ 37905 | consumed samples: 2152960 | consumed tokens: 4409262080 | elapsed time per iteration (s): 0.18 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 3.045296E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1459.460 | TFLOPs: 9.29 | +31: iteration 8420/ 37905 | consumed samples: 2155520 | consumed tokens: 4414504960 | elapsed time per iteration (s): 0.18 | learning rate: 1.790E-04 | global batch size: 256 | lm loss: 3.082344E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.240 | TFLOPs: 8.93 | +31: iteration 8430/ 37905 | consumed samples: 2158080 | consumed tokens: 4419747840 | elapsed time per iteration (s): 0.19 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 3.115433E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1337.967 | TFLOPs: 8.52 | +31: iteration 8440/ 37905 | consumed samples: 2160640 | consumed tokens: 4424990720 | elapsed time per iteration (s): 0.19 | learning rate: 1.789E-04 | global batch size: 256 | lm loss: 3.092269E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1350.553 | TFLOPs: 8.60 | +31: iteration 8450/ 37905 | consumed samples: 2163200 | consumed tokens: 4430233600 | elapsed time per iteration (s): 0.23 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 3.101455E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.374 | TFLOPs: 6.96 | +31: iteration 8460/ 37905 | consumed samples: 2165760 | consumed tokens: 4435476480 | elapsed time per iteration (s): 0.20 | learning rate: 1.788E-04 | global batch size: 256 | lm loss: 3.130292E+00 | grad norm: 0.374 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.368 | TFLOPs: 8.25 | +31: iteration 8470/ 37905 | consumed samples: 2168320 | consumed tokens: 4440719360 | elapsed time per iteration (s): 0.18 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 3.090108E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1404.854 | TFLOPs: 8.95 | +31: iteration 8480/ 37905 | consumed samples: 2170880 | consumed tokens: 4445962240 | elapsed time per iteration (s): 0.20 | learning rate: 1.787E-04 | global batch size: 256 | lm loss: 3.084791E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.690 | TFLOPs: 8.12 | +31: iteration 8490/ 37905 | consumed samples: 2173440 | consumed tokens: 4451205120 | elapsed time per iteration (s): 0.19 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.120190E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.750 | TFLOPs: 8.46 | +31: iteration 8500/ 37905 | consumed samples: 2176000 | consumed tokens: 4456448000 | elapsed time per iteration (s): 0.21 | learning rate: 1.786E-04 | global batch size: 256 | lm loss: 3.122436E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1230.325 | TFLOPs: 7.84 | +31: iteration 8510/ 37905 | consumed samples: 2178560 | consumed tokens: 4461690880 | elapsed time per iteration (s): 0.19 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 3.049464E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1382.694 | TFLOPs: 8.81 | +31: iteration 8520/ 37905 | consumed samples: 2181120 | consumed tokens: 4466933760 | elapsed time per iteration (s): 0.21 | learning rate: 1.785E-04 | global batch size: 256 | lm loss: 3.070513E+00 | grad norm: 0.381 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.405 | TFLOPs: 7.75 | +31: iteration 8530/ 37905 | consumed samples: 2183680 | consumed tokens: 4472176640 | elapsed time per iteration (s): 0.19 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.075942E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.591 | TFLOPs: 8.38 | +31: iteration 8540/ 37905 | consumed samples: 2186240 | consumed tokens: 4477419520 | elapsed time per iteration (s): 0.23 | learning rate: 1.784E-04 | global batch size: 256 | lm loss: 3.087451E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.617 | TFLOPs: 7.14 | +31: iteration 8550/ 37905 | consumed samples: 2188800 | consumed tokens: 4482662400 | elapsed time per iteration (s): 0.20 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 3.087570E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.050 | TFLOPs: 8.15 | +31: iteration 8560/ 37905 | consumed samples: 2191360 | consumed tokens: 4487905280 | elapsed time per iteration (s): 0.21 | learning rate: 1.783E-04 | global batch size: 256 | lm loss: 3.096640E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.435 | TFLOPs: 7.69 | +31: iteration 8570/ 37905 | consumed samples: 2193920 | consumed tokens: 4493148160 | elapsed time per iteration (s): 0.23 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 3.096083E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.037 | TFLOPs: 7.03 | +31: iteration 8580/ 37905 | consumed samples: 2196480 | consumed tokens: 4498391040 | elapsed time per iteration (s): 0.19 | learning rate: 1.782E-04 | global batch size: 256 | lm loss: 3.098652E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.405 | TFLOPs: 8.78 | +31: iteration 8590/ 37905 | consumed samples: 2199040 | consumed tokens: 4503633920 | elapsed time per iteration (s): 0.20 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.130043E+00 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.625 | TFLOPs: 8.05 | +31: iteration 8600/ 37905 | consumed samples: 2201600 | consumed tokens: 4508876800 | elapsed time per iteration (s): 0.19 | learning rate: 1.781E-04 | global batch size: 256 | lm loss: 3.119692E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.661 | TFLOPs: 8.38 | +31: iteration 8610/ 37905 | consumed samples: 2204160 | consumed tokens: 4514119680 | elapsed time per iteration (s): 0.20 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 3.085793E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.226 | TFLOPs: 8.33 | +31: iteration 8620/ 37905 | consumed samples: 2206720 | consumed tokens: 4519362560 | elapsed time per iteration (s): 0.19 | learning rate: 1.780E-04 | global batch size: 256 | lm loss: 3.130695E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1318.409 | TFLOPs: 8.40 | +31: iteration 8630/ 37905 | consumed samples: 2209280 | consumed tokens: 4524605440 | elapsed time per iteration (s): 0.20 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 3.075235E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1262.894 | TFLOPs: 8.04 | +31: iteration 8640/ 37905 | consumed samples: 2211840 | consumed tokens: 4529848320 | elapsed time per iteration (s): 0.20 | learning rate: 1.779E-04 | global batch size: 256 | lm loss: 3.076336E+00 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.803 | TFLOPs: 8.17 | +31: iteration 8650/ 37905 | consumed samples: 2214400 | consumed tokens: 4535091200 | elapsed time per iteration (s): 0.19 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 3.063183E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1356.576 | TFLOPs: 8.64 | +31: iteration 8660/ 37905 | consumed samples: 2216960 | consumed tokens: 4540334080 | elapsed time per iteration (s): 0.21 | learning rate: 1.778E-04 | global batch size: 256 | lm loss: 3.097391E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.703 | TFLOPs: 7.87 | +31: iteration 8670/ 37905 | consumed samples: 2219520 | consumed tokens: 4545576960 | elapsed time per iteration (s): 0.19 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.090557E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.773 | TFLOPs: 8.39 | +31: iteration 8680/ 37905 | consumed samples: 2222080 | consumed tokens: 4550819840 | elapsed time per iteration (s): 0.22 | learning rate: 1.777E-04 | global batch size: 256 | lm loss: 3.088345E+00 | grad norm: 0.348 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.718 | TFLOPs: 7.34 | +31: iteration 8690/ 37905 | consumed samples: 2224640 | consumed tokens: 4556062720 | elapsed time per iteration (s): 0.20 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.070537E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.110 | TFLOPs: 8.04 | +31: iteration 8700/ 37905 | consumed samples: 2227200 | consumed tokens: 4561305600 | elapsed time per iteration (s): 0.19 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.084004E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.629 | TFLOPs: 8.43 | +31: iteration 8710/ 37905 | consumed samples: 2229760 | consumed tokens: 4566548480 | elapsed time per iteration (s): 0.19 | learning rate: 1.776E-04 | global batch size: 256 | lm loss: 3.066282E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.722 | TFLOPs: 8.41 | +31: iteration 8720/ 37905 | consumed samples: 2232320 | consumed tokens: 4571791360 | elapsed time per iteration (s): 0.20 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 3.061543E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.077 | TFLOPs: 8.04 | +31: iteration 8730/ 37905 | consumed samples: 2234880 | consumed tokens: 4577034240 | elapsed time per iteration (s): 0.19 | learning rate: 1.775E-04 | global batch size: 256 | lm loss: 3.117657E+00 | grad norm: 0.354 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.957 | TFLOPs: 8.54 | +31: iteration 8740/ 37905 | consumed samples: 2237440 | consumed tokens: 4582277120 | elapsed time per iteration (s): 0.19 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 3.052588E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1377.498 | TFLOPs: 8.77 | +31: iteration 8750/ 37905 | consumed samples: 2240000 | consumed tokens: 4587520000 | elapsed time per iteration (s): 0.21 | learning rate: 1.774E-04 | global batch size: 256 | lm loss: 3.101656E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.160 | TFLOPs: 7.89 | +31: iteration 8760/ 37905 | consumed samples: 2242560 | consumed tokens: 4592762880 | elapsed time per iteration (s): 0.19 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.095959E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1361.662 | TFLOPs: 8.67 | +31: iteration 8770/ 37905 | consumed samples: 2245120 | consumed tokens: 4598005760 | elapsed time per iteration (s): 0.21 | learning rate: 1.773E-04 | global batch size: 256 | lm loss: 3.060275E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.716 | TFLOPs: 7.72 | +31: iteration 8780/ 37905 | consumed samples: 2247680 | consumed tokens: 4603248640 | elapsed time per iteration (s): 0.20 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 3.078140E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.582 | TFLOPs: 8.05 | +31: iteration 8790/ 37905 | consumed samples: 2250240 | consumed tokens: 4608491520 | elapsed time per iteration (s): 0.19 | learning rate: 1.772E-04 | global batch size: 256 | lm loss: 3.069936E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1329.266 | TFLOPs: 8.47 | +31: iteration 8800/ 37905 | consumed samples: 2252800 | consumed tokens: 4613734400 | elapsed time per iteration (s): 0.19 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 3.095477E+00 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.994 | TFLOPs: 8.51 | +31: iteration 8810/ 37905 | consumed samples: 2255360 | consumed tokens: 4618977280 | elapsed time per iteration (s): 0.18 | learning rate: 1.771E-04 | global batch size: 256 | lm loss: 3.069435E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1401.036 | TFLOPs: 8.92 | +31: iteration 8820/ 37905 | consumed samples: 2257920 | consumed tokens: 4624220160 | elapsed time per iteration (s): 0.19 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.093745E+00 | grad norm: 0.380 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.671 | TFLOPs: 8.53 | +31: iteration 8830/ 37905 | consumed samples: 2260480 | consumed tokens: 4629463040 | elapsed time per iteration (s): 0.20 | learning rate: 1.770E-04 | global batch size: 256 | lm loss: 3.093357E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.810 | TFLOPs: 8.04 | +31: iteration 8840/ 37905 | consumed samples: 2263040 | consumed tokens: 4634705920 | elapsed time per iteration (s): 0.18 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 3.102888E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1393.686 | TFLOPs: 8.88 | +31: iteration 8850/ 37905 | consumed samples: 2265600 | consumed tokens: 4639948800 | elapsed time per iteration (s): 0.20 | learning rate: 1.769E-04 | global batch size: 256 | lm loss: 3.079284E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.381 | TFLOPs: 8.09 | +31: iteration 8860/ 37905 | consumed samples: 2268160 | consumed tokens: 4645191680 | elapsed time per iteration (s): 0.20 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 3.094477E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.827 | TFLOPs: 8.17 | +31: iteration 8870/ 37905 | consumed samples: 2270720 | consumed tokens: 4650434560 | elapsed time per iteration (s): 0.20 | learning rate: 1.768E-04 | global batch size: 256 | lm loss: 3.066809E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.892 | TFLOPs: 8.13 | +31: iteration 8880/ 37905 | consumed samples: 2273280 | consumed tokens: 4655677440 | elapsed time per iteration (s): 0.17 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 3.090144E+00 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1468.350 | TFLOPs: 9.35 | +31: iteration 8890/ 37905 | consumed samples: 2275840 | consumed tokens: 4660920320 | elapsed time per iteration (s): 0.18 | learning rate: 1.767E-04 | global batch size: 256 | lm loss: 3.055863E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.875 | TFLOPs: 8.93 | +31: iteration 8900/ 37905 | consumed samples: 2278400 | consumed tokens: 4666163200 | elapsed time per iteration (s): 0.18 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.094965E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1406.701 | TFLOPs: 8.96 | +31: iteration 8910/ 37905 | consumed samples: 2280960 | consumed tokens: 4671406080 | elapsed time per iteration (s): 0.19 | learning rate: 1.766E-04 | global batch size: 256 | lm loss: 3.087958E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.820 | TFLOPs: 8.76 | +31: iteration 8920/ 37905 | consumed samples: 2283520 | consumed tokens: 4676648960 | elapsed time per iteration (s): 0.18 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 3.059607E+00 | grad norm: 0.347 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.494 | TFLOPs: 8.93 | +31: iteration 8930/ 37905 | consumed samples: 2286080 | consumed tokens: 4681891840 | elapsed time per iteration (s): 0.21 | learning rate: 1.765E-04 | global batch size: 256 | lm loss: 3.068695E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.619 | TFLOPs: 7.93 | +31: iteration 8940/ 37905 | consumed samples: 2288640 | consumed tokens: 4687134720 | elapsed time per iteration (s): 0.21 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 3.075258E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.629 | TFLOPs: 7.81 | +31: iteration 8950/ 37905 | consumed samples: 2291200 | consumed tokens: 4692377600 | elapsed time per iteration (s): 0.20 | learning rate: 1.764E-04 | global batch size: 256 | lm loss: 3.083141E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.539 | TFLOPs: 8.36 | +31: iteration 8960/ 37905 | consumed samples: 2293760 | consumed tokens: 4697620480 | elapsed time per iteration (s): 0.20 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 3.075677E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.511 | TFLOPs: 7.96 | +31: iteration 8970/ 37905 | consumed samples: 2296320 | consumed tokens: 4702863360 | elapsed time per iteration (s): 0.20 | learning rate: 1.763E-04 | global batch size: 256 | lm loss: 3.081347E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.639 | TFLOPs: 8.17 | +31: iteration 8980/ 37905 | consumed samples: 2298880 | consumed tokens: 4708106240 | elapsed time per iteration (s): 0.20 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 3.060395E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.794 | TFLOPs: 8.09 | +31: iteration 8990/ 37905 | consumed samples: 2301440 | consumed tokens: 4713349120 | elapsed time per iteration (s): 0.21 | learning rate: 1.762E-04 | global batch size: 256 | lm loss: 3.059034E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.347 | TFLOPs: 7.71 | +31: iteration 9000/ 37905 | consumed samples: 2304000 | consumed tokens: 4718592000 | elapsed time per iteration (s): 0.20 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.071237E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1268.495 | TFLOPs: 8.08 | + 0: saving checkpoint at iteration 9000 to checkpoints_83m +31: ------------------------------------------------------------------------------------------ +31: valid loss at iteration 9000 | lm loss value: 2.895627E+00 | lm loss PPL: 1.809484E+01 | +31: ------------------------------------------------------------------------------------------ + 0: [2022-11-24 14:44:03,861] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step9000 is begin to save! + 0: [2022-11-24 14:44:03,868] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:44:03,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:44:03,940] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:44:03,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:44:03,952] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:44:03,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:44:03,964] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:44:03,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:44:03,975] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:44:03,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:44:03,986] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:44:03,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:44:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:44:04,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:44:04,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:44:04,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:44:04,019] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:44:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:44:04,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:44:04,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:44:04,041] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:44:04,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:44:04,051] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:44:04,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:44:04,053] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step9000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:44:04,053] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:44:04,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:44:04,120] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step9000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:44:04,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 14:44:04,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 14:44:04,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +19: [2022-11-24 14:44:04,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:44:04,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 3: [2022-11-24 14:44:04,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +23: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:44:04,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 4: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:44:04,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +30: [2022-11-24 14:44:04,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 5: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +26: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +17: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +31: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +11: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +11: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +10: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +10: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +22: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +15: [2022-11-24 14:44:04,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 6: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:44:04,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:44:04,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:44:04,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +27: [2022-11-24 14:44:04,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:44:04,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +19: [2022-11-24 14:44:04,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:44:04,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:44:04,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:44:04,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 4: [2022-11-24 14:44:04,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:44:04,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +23: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:44:04,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +30: [2022-11-24 14:44:04,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 5: [2022-11-24 14:44:04,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +26: [2022-11-24 14:44:04,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:44:04,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:44:04,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +10: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +15: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 6: [2022-11-24 14:44:04,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +21: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +31: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:44:04,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +22: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +27: [2022-11-24 14:44:04,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +19: [2022-11-24 14:44:04,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:44:04,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:44:04,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:44:04,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +17: [2022-11-24 14:44:04,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:44:04,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 3: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +25: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 4: [2022-11-24 14:44:04,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:44:04,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:44:04,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +23: [2022-11-24 14:44:04,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:44:04,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +26: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:44:04,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +11: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,149] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +11: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 5: [2022-11-24 14:44:04,149] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:44:04,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:44:04,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +10: [2022-11-24 14:44:04,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 14:44:04,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 6: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +15: [2022-11-24 14:44:04,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:44:04,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +31: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,151] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 14:44:04,151] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,152] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +22: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,153] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +27: [2022-11-24 14:44:04,153] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,153] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +19: [2022-11-24 14:44:04,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:44:04,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:44:04,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +17: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:44:04,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 3: [2022-11-24 14:44:04,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,154] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +14: [2022-11-24 14:44:04,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +23: [2022-11-24 14:44:04,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,155] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +23: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:44:04,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 5: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +26: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:44:04,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +30: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,156] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +11: [2022-11-24 14:44:04,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:44:04,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:44:04,157] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,157] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:44:04,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 6: [2022-11-24 14:44:04,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +10: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:44:04,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:44:04,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +15: [2022-11-24 14:44:04,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +31: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:44:04,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:44:04,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 14:44:04,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +22: [2022-11-24 14:44:04,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +27: [2022-11-24 14:44:04,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:44:04,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +19: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +17: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:44:04,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:44:04,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 3: [2022-11-24 14:44:04,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:44:04,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +25: [2022-11-24 14:44:04,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:44:04,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 4: [2022-11-24 14:44:04,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:44:04,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:44:04,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +23: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +30: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 5: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +11: [2022-11-24 14:44:04,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +26: [2022-11-24 14:44:04,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:44:04,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +10: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +15: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:44:04,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +31: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:44:04,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +22: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:44:04,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +19: [2022-11-24 14:44:04,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:44:04,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:44:04,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 3: [2022-11-24 14:44:04,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 4: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +25: [2022-11-24 14:44:04,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +23: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +30: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 5: [2022-11-24 14:44:04,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +11: [2022-11-24 14:44:04,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +26: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:44:04,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:44:04,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 6: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +15: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +10: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:44:04,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:44:04,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +31: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +21: [2022-11-24 14:44:04,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +16: [2022-11-24 14:44:04,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:44:04,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +27: [2022-11-24 14:44:04,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:44:04,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:44:04,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +19: [2022-11-24 14:44:04,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +17: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 3: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +17: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +31: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +23: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +14: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +22: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 4: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +21: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +25: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 4: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +20: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +15: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +23: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +10: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +26: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +23: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +10: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +30: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +19: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 3: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 6: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +15: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +21: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +18: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +17: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +11: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +12: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +30: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 1: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +26: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +24: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +21: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +17: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +11: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 9: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +31: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +25: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +16: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +22: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 2: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +13: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +13: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 7: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +11: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +31: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 5: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +12: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +29: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +27: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 8: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +28: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +27: [2022-11-24 14:44:04,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step9000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +28: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +27: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! +16: [2022-11-24 14:44:04,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step9000 is ready now! + 0: successfully saved checkpoint at iteration 9000 to checkpoints_83m +31: time (ms) | save-checkpoint: 322.08 +31: iteration 9010/ 37905 | consumed samples: 2306560 | consumed tokens: 4723834880 | elapsed time per iteration (s): 0.24 | learning rate: 1.761E-04 | global batch size: 256 | lm loss: 3.093484E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.562 | TFLOPs: 6.92 | +31: iteration 9020/ 37905 | consumed samples: 2309120 | consumed tokens: 4729077760 | elapsed time per iteration (s): 0.19 | learning rate: 1.760E-04 | global batch size: 256 | lm loss: 3.066960E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.130 | TFLOPs: 8.54 | +31: iteration 9030/ 37905 | consumed samples: 2311680 | consumed tokens: 4734320640 | elapsed time per iteration (s): 0.21 | learning rate: 1.759E-04 | global batch size: 256 | lm loss: 3.102429E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.707 | TFLOPs: 7.68 | +31: iteration 9040/ 37905 | consumed samples: 2314240 | consumed tokens: 4739563520 | elapsed time per iteration (s): 0.21 | learning rate: 1.759E-04 | global batch size: 256 | lm loss: 3.089232E+00 | grad norm: 0.359 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.837 | TFLOPs: 7.90 | +31: iteration 9050/ 37905 | consumed samples: 2316800 | consumed tokens: 4744806400 | elapsed time per iteration (s): 0.20 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.112792E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.272 | TFLOPs: 8.17 | +31: iteration 9060/ 37905 | consumed samples: 2319360 | consumed tokens: 4750049280 | elapsed time per iteration (s): 0.19 | learning rate: 1.758E-04 | global batch size: 256 | lm loss: 3.099303E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1339.398 | TFLOPs: 8.53 | +31: iteration 9070/ 37905 | consumed samples: 2321920 | consumed tokens: 4755292160 | elapsed time per iteration (s): 0.20 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 3.079814E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.513 | TFLOPs: 7.99 | +31: iteration 9080/ 37905 | consumed samples: 2324480 | consumed tokens: 4760535040 | elapsed time per iteration (s): 0.19 | learning rate: 1.757E-04 | global batch size: 256 | lm loss: 3.114006E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.564 | TFLOPs: 8.51 | +31: iteration 9090/ 37905 | consumed samples: 2327040 | consumed tokens: 4765777920 | elapsed time per iteration (s): 0.20 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.063664E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.578 | TFLOPs: 8.00 | +31: iteration 9100/ 37905 | consumed samples: 2329600 | consumed tokens: 4771020800 | elapsed time per iteration (s): 0.19 | learning rate: 1.756E-04 | global batch size: 256 | lm loss: 3.098560E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.879 | TFLOPs: 8.54 | +31: iteration 9110/ 37905 | consumed samples: 2332160 | consumed tokens: 4776263680 | elapsed time per iteration (s): 0.22 | learning rate: 1.755E-04 | global batch size: 256 | lm loss: 3.055024E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.563 | TFLOPs: 7.43 | +31: iteration 9120/ 37905 | consumed samples: 2334720 | consumed tokens: 4781506560 | elapsed time per iteration (s): 0.24 | learning rate: 1.755E-04 | global batch size: 256 | lm loss: 3.094477E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.977 | TFLOPs: 6.69 | +31: iteration 9130/ 37905 | consumed samples: 2337280 | consumed tokens: 4786749440 | elapsed time per iteration (s): 0.19 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.083857E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.446 | TFLOPs: 8.51 | +31: iteration 9140/ 37905 | consumed samples: 2339840 | consumed tokens: 4791992320 | elapsed time per iteration (s): 0.18 | learning rate: 1.754E-04 | global batch size: 256 | lm loss: 3.066035E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1391.892 | TFLOPs: 8.86 | +31: iteration 9150/ 37905 | consumed samples: 2342400 | consumed tokens: 4797235200 | elapsed time per iteration (s): 0.18 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.087670E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1387.960 | TFLOPs: 8.84 | +31: iteration 9160/ 37905 | consumed samples: 2344960 | consumed tokens: 4802478080 | elapsed time per iteration (s): 0.19 | learning rate: 1.753E-04 | global batch size: 256 | lm loss: 3.095067E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.687 | TFLOPs: 8.63 | +31: iteration 9170/ 37905 | consumed samples: 2347520 | consumed tokens: 4807720960 | elapsed time per iteration (s): 0.19 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 3.136984E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1353.237 | TFLOPs: 8.62 | +31: iteration 9180/ 37905 | consumed samples: 2350080 | consumed tokens: 4812963840 | elapsed time per iteration (s): 0.19 | learning rate: 1.752E-04 | global batch size: 256 | lm loss: 3.085955E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.353 | TFLOPs: 8.41 | +31: iteration 9190/ 37905 | consumed samples: 2352640 | consumed tokens: 4818206720 | elapsed time per iteration (s): 0.19 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.092990E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1357.542 | TFLOPs: 8.65 | +31: iteration 9200/ 37905 | consumed samples: 2355200 | consumed tokens: 4823449600 | elapsed time per iteration (s): 0.18 | learning rate: 1.751E-04 | global batch size: 256 | lm loss: 3.071331E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1392.639 | TFLOPs: 8.87 | +31: iteration 9210/ 37905 | consumed samples: 2357760 | consumed tokens: 4828692480 | elapsed time per iteration (s): 0.18 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 3.068826E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1459.335 | TFLOPs: 9.29 | +31: iteration 9220/ 37905 | consumed samples: 2360320 | consumed tokens: 4833935360 | elapsed time per iteration (s): 0.20 | learning rate: 1.750E-04 | global batch size: 256 | lm loss: 3.025794E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.693 | TFLOPs: 8.32 | +31: iteration 9230/ 37905 | consumed samples: 2362880 | consumed tokens: 4839178240 | elapsed time per iteration (s): 0.21 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 3.094463E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.399 | TFLOPs: 7.80 | +31: iteration 9240/ 37905 | consumed samples: 2365440 | consumed tokens: 4844421120 | elapsed time per iteration (s): 0.21 | learning rate: 1.749E-04 | global batch size: 256 | lm loss: 3.073256E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.033 | TFLOPs: 7.78 | +31: iteration 9250/ 37905 | consumed samples: 2368000 | consumed tokens: 4849664000 | elapsed time per iteration (s): 0.21 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 3.074129E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.153 | TFLOPs: 7.81 | +31: iteration 9260/ 37905 | consumed samples: 2370560 | consumed tokens: 4854906880 | elapsed time per iteration (s): 0.19 | learning rate: 1.748E-04 | global batch size: 256 | lm loss: 3.111155E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.688 | TFLOPs: 8.51 | +31: iteration 9270/ 37905 | consumed samples: 2373120 | consumed tokens: 4860149760 | elapsed time per iteration (s): 0.21 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 3.095539E+00 | grad norm: 0.342 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.348 | TFLOPs: 7.81 | +31: iteration 9280/ 37905 | consumed samples: 2375680 | consumed tokens: 4865392640 | elapsed time per iteration (s): 0.22 | learning rate: 1.747E-04 | global batch size: 256 | lm loss: 3.097787E+00 | grad norm: 0.332 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.182 | TFLOPs: 7.41 | +31: iteration 9290/ 37905 | consumed samples: 2378240 | consumed tokens: 4870635520 | elapsed time per iteration (s): 0.23 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 3.081395E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.586 | TFLOPs: 7.17 | +31: iteration 9300/ 37905 | consumed samples: 2380800 | consumed tokens: 4875878400 | elapsed time per iteration (s): 0.22 | learning rate: 1.746E-04 | global batch size: 256 | lm loss: 3.056562E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.082 | TFLOPs: 7.45 | +31: iteration 9310/ 37905 | consumed samples: 2383360 | consumed tokens: 4881121280 | elapsed time per iteration (s): 0.21 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 3.085921E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.556 | TFLOPs: 7.90 | +31: iteration 9320/ 37905 | consumed samples: 2385920 | consumed tokens: 4886364160 | elapsed time per iteration (s): 0.21 | learning rate: 1.745E-04 | global batch size: 256 | lm loss: 3.082020E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.513 | TFLOPs: 7.61 | +31: iteration 9330/ 37905 | consumed samples: 2388480 | consumed tokens: 4891607040 | elapsed time per iteration (s): 0.21 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 3.111669E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.187 | TFLOPs: 7.78 | +31: iteration 9340/ 37905 | consumed samples: 2391040 | consumed tokens: 4896849920 | elapsed time per iteration (s): 0.20 | learning rate: 1.744E-04 | global batch size: 256 | lm loss: 3.089274E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.169 | TFLOPs: 8.10 | +31: iteration 9350/ 37905 | consumed samples: 2393600 | consumed tokens: 4902092800 | elapsed time per iteration (s): 0.20 | learning rate: 1.743E-04 | global batch size: 256 | lm loss: 3.090310E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.828 | TFLOPs: 8.07 | +31: iteration 9360/ 37905 | consumed samples: 2396160 | consumed tokens: 4907335680 | elapsed time per iteration (s): 0.20 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 3.040979E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.773 | TFLOPs: 8.02 | +31: iteration 9370/ 37905 | consumed samples: 2398720 | consumed tokens: 4912578560 | elapsed time per iteration (s): 0.19 | learning rate: 1.742E-04 | global batch size: 256 | lm loss: 3.080066E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1368.453 | TFLOPs: 8.72 | +31: iteration 9380/ 37905 | consumed samples: 2401280 | consumed tokens: 4917821440 | elapsed time per iteration (s): 0.20 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 3.089351E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.541 | TFLOPs: 8.10 | +31: iteration 9390/ 37905 | consumed samples: 2403840 | consumed tokens: 4923064320 | elapsed time per iteration (s): 0.19 | learning rate: 1.741E-04 | global batch size: 256 | lm loss: 3.059678E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1373.627 | TFLOPs: 8.75 | +31: iteration 9400/ 37905 | consumed samples: 2406400 | consumed tokens: 4928307200 | elapsed time per iteration (s): 0.19 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.092009E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.870 | TFLOPs: 8.69 | +31: iteration 9410/ 37905 | consumed samples: 2408960 | consumed tokens: 4933550080 | elapsed time per iteration (s): 0.18 | learning rate: 1.740E-04 | global batch size: 256 | lm loss: 3.027060E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1393.283 | TFLOPs: 8.87 | +31: iteration 9420/ 37905 | consumed samples: 2411520 | consumed tokens: 4938792960 | elapsed time per iteration (s): 0.21 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.098677E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.198 | TFLOPs: 7.78 | +31: iteration 9430/ 37905 | consumed samples: 2414080 | consumed tokens: 4944035840 | elapsed time per iteration (s): 0.20 | learning rate: 1.739E-04 | global batch size: 256 | lm loss: 3.061754E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.559 | TFLOPs: 8.14 | +31: iteration 9440/ 37905 | consumed samples: 2416640 | consumed tokens: 4949278720 | elapsed time per iteration (s): 0.20 | learning rate: 1.738E-04 | global batch size: 256 | lm loss: 3.086905E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.445 | TFLOPs: 8.11 | +31: iteration 9450/ 37905 | consumed samples: 2419200 | consumed tokens: 4954521600 | elapsed time per iteration (s): 0.22 | learning rate: 1.738E-04 | global batch size: 256 | lm loss: 3.126756E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.545 | TFLOPs: 7.26 | +31: iteration 9460/ 37905 | consumed samples: 2421760 | consumed tokens: 4959764480 | elapsed time per iteration (s): 0.23 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 3.098085E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.878 | TFLOPs: 7.22 | +31: iteration 9470/ 37905 | consumed samples: 2424320 | consumed tokens: 4965007360 | elapsed time per iteration (s): 0.19 | learning rate: 1.737E-04 | global batch size: 256 | lm loss: 3.099734E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1338.850 | TFLOPs: 8.53 | +31: iteration 9480/ 37905 | consumed samples: 2426880 | consumed tokens: 4970250240 | elapsed time per iteration (s): 0.18 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 3.040200E+00 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1394.715 | TFLOPs: 8.88 | +31: iteration 9490/ 37905 | consumed samples: 2429440 | consumed tokens: 4975493120 | elapsed time per iteration (s): 0.22 | learning rate: 1.736E-04 | global batch size: 256 | lm loss: 3.041342E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1180.359 | TFLOPs: 7.52 | +31: iteration 9500/ 37905 | consumed samples: 2432000 | consumed tokens: 4980736000 | elapsed time per iteration (s): 0.19 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.081780E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.496 | TFLOPs: 8.46 | +31: iteration 9510/ 37905 | consumed samples: 2434560 | consumed tokens: 4985978880 | elapsed time per iteration (s): 0.21 | learning rate: 1.735E-04 | global batch size: 256 | lm loss: 3.080206E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.295 | TFLOPs: 7.68 | +31: iteration 9520/ 37905 | consumed samples: 2437120 | consumed tokens: 4991221760 | elapsed time per iteration (s): 0.19 | learning rate: 1.734E-04 | global batch size: 256 | lm loss: 3.057098E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.168 | TFLOPs: 8.43 | +31: iteration 9530/ 37905 | consumed samples: 2439680 | consumed tokens: 4996464640 | elapsed time per iteration (s): 0.21 | learning rate: 1.734E-04 | global batch size: 256 | lm loss: 3.101397E+00 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.011 | TFLOPs: 7.81 | +31: iteration 9540/ 37905 | consumed samples: 2442240 | consumed tokens: 5001707520 | elapsed time per iteration (s): 0.18 | learning rate: 1.733E-04 | global batch size: 256 | lm loss: 3.101349E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1397.419 | TFLOPs: 8.90 | +31: iteration 9550/ 37905 | consumed samples: 2444800 | consumed tokens: 5006950400 | elapsed time per iteration (s): 0.20 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 3.091311E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1276.423 | TFLOPs: 8.13 | +31: iteration 9560/ 37905 | consumed samples: 2447360 | consumed tokens: 5012193280 | elapsed time per iteration (s): 0.18 | learning rate: 1.732E-04 | global batch size: 256 | lm loss: 3.089452E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1436.172 | TFLOPs: 9.15 | +31: iteration 9570/ 37905 | consumed samples: 2449920 | consumed tokens: 5017436160 | elapsed time per iteration (s): 0.20 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.011984E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.150 | TFLOPs: 8.14 | +31: iteration 9580/ 37905 | consumed samples: 2452480 | consumed tokens: 5022679040 | elapsed time per iteration (s): 0.18 | learning rate: 1.731E-04 | global batch size: 256 | lm loss: 3.078909E+00 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1394.035 | TFLOPs: 8.88 | +31: iteration 9590/ 37905 | consumed samples: 2455040 | consumed tokens: 5027921920 | elapsed time per iteration (s): 0.21 | learning rate: 1.730E-04 | global batch size: 256 | lm loss: 3.045832E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.893 | TFLOPs: 7.83 | +31: iteration 9600/ 37905 | consumed samples: 2457600 | consumed tokens: 5033164800 | elapsed time per iteration (s): 0.18 | learning rate: 1.730E-04 | global batch size: 256 | lm loss: 3.051575E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1386.182 | TFLOPs: 8.83 | +31: iteration 9610/ 37905 | consumed samples: 2460160 | consumed tokens: 5038407680 | elapsed time per iteration (s): 0.18 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 3.049423E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1384.551 | TFLOPs: 8.82 | +31: iteration 9620/ 37905 | consumed samples: 2462720 | consumed tokens: 5043650560 | elapsed time per iteration (s): 0.18 | learning rate: 1.729E-04 | global batch size: 256 | lm loss: 3.123434E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1400.588 | TFLOPs: 8.92 | +31: iteration 9630/ 37905 | consumed samples: 2465280 | consumed tokens: 5048893440 | elapsed time per iteration (s): 0.20 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 3.088993E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.322 | TFLOPs: 8.11 | +31: iteration 9640/ 37905 | consumed samples: 2467840 | consumed tokens: 5054136320 | elapsed time per iteration (s): 0.18 | learning rate: 1.728E-04 | global batch size: 256 | lm loss: 3.043120E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1389.833 | TFLOPs: 8.85 | +31: iteration 9650/ 37905 | consumed samples: 2470400 | consumed tokens: 5059379200 | elapsed time per iteration (s): 0.21 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 3.083534E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.452 | TFLOPs: 7.66 | +31: iteration 9660/ 37905 | consumed samples: 2472960 | consumed tokens: 5064622080 | elapsed time per iteration (s): 0.19 | learning rate: 1.727E-04 | global batch size: 256 | lm loss: 3.084276E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.966 | TFLOPs: 8.46 | +31: iteration 9670/ 37905 | consumed samples: 2475520 | consumed tokens: 5069864960 | elapsed time per iteration (s): 0.19 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.052349E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1363.483 | TFLOPs: 8.68 | +31: iteration 9680/ 37905 | consumed samples: 2478080 | consumed tokens: 5075107840 | elapsed time per iteration (s): 0.20 | learning rate: 1.726E-04 | global batch size: 256 | lm loss: 3.059976E+00 | grad norm: 0.355 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.816 | TFLOPs: 8.22 | +31: iteration 9690/ 37905 | consumed samples: 2480640 | consumed tokens: 5080350720 | elapsed time per iteration (s): 0.19 | learning rate: 1.725E-04 | global batch size: 256 | lm loss: 3.054291E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.116 | TFLOPs: 8.38 | +31: iteration 9700/ 37905 | consumed samples: 2483200 | consumed tokens: 5085593600 | elapsed time per iteration (s): 0.21 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 3.067420E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.777 | TFLOPs: 7.73 | +31: iteration 9710/ 37905 | consumed samples: 2485760 | consumed tokens: 5090836480 | elapsed time per iteration (s): 0.19 | learning rate: 1.724E-04 | global batch size: 256 | lm loss: 3.059541E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1334.921 | TFLOPs: 8.50 | +31: iteration 9720/ 37905 | consumed samples: 2488320 | consumed tokens: 5096079360 | elapsed time per iteration (s): 0.19 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 3.061406E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.146 | TFLOPs: 8.46 | +31: iteration 9730/ 37905 | consumed samples: 2490880 | consumed tokens: 5101322240 | elapsed time per iteration (s): 0.21 | learning rate: 1.723E-04 | global batch size: 256 | lm loss: 3.121670E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.793 | TFLOPs: 7.86 | +31: iteration 9740/ 37905 | consumed samples: 2493440 | consumed tokens: 5106565120 | elapsed time per iteration (s): 0.19 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 3.081169E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1337.347 | TFLOPs: 8.52 | +31: iteration 9750/ 37905 | consumed samples: 2496000 | consumed tokens: 5111808000 | elapsed time per iteration (s): 0.20 | learning rate: 1.722E-04 | global batch size: 256 | lm loss: 3.059176E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.788 | TFLOPs: 8.06 | +31: iteration 9760/ 37905 | consumed samples: 2498560 | consumed tokens: 5117050880 | elapsed time per iteration (s): 0.20 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 3.056945E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.628 | TFLOPs: 8.11 | +31: iteration 9770/ 37905 | consumed samples: 2501120 | consumed tokens: 5122293760 | elapsed time per iteration (s): 0.22 | learning rate: 1.721E-04 | global batch size: 256 | lm loss: 3.070915E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.399 | TFLOPs: 7.54 | +31: iteration 9780/ 37905 | consumed samples: 2503680 | consumed tokens: 5127536640 | elapsed time per iteration (s): 0.18 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 3.098194E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1394.876 | TFLOPs: 8.88 | +31: iteration 9790/ 37905 | consumed samples: 2506240 | consumed tokens: 5132779520 | elapsed time per iteration (s): 0.21 | learning rate: 1.720E-04 | global batch size: 256 | lm loss: 3.051367E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.739 | TFLOPs: 7.76 | +31: iteration 9800/ 37905 | consumed samples: 2508800 | consumed tokens: 5138022400 | elapsed time per iteration (s): 0.19 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.083095E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.640 | TFLOPs: 8.47 | +31: iteration 9810/ 37905 | consumed samples: 2511360 | consumed tokens: 5143265280 | elapsed time per iteration (s): 0.20 | learning rate: 1.719E-04 | global batch size: 256 | lm loss: 3.076196E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1303.696 | TFLOPs: 8.30 | +31: iteration 9820/ 37905 | consumed samples: 2513920 | consumed tokens: 5148508160 | elapsed time per iteration (s): 0.19 | learning rate: 1.718E-04 | global batch size: 256 | lm loss: 3.049511E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.437 | TFLOPs: 8.49 | +31: iteration 9830/ 37905 | consumed samples: 2516480 | consumed tokens: 5153751040 | elapsed time per iteration (s): 0.20 | learning rate: 1.717E-04 | global batch size: 256 | lm loss: 3.078251E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.140 | TFLOPs: 8.25 | +31: iteration 9840/ 37905 | consumed samples: 2519040 | consumed tokens: 5158993920 | elapsed time per iteration (s): 0.19 | learning rate: 1.717E-04 | global batch size: 256 | lm loss: 3.029941E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1376.063 | TFLOPs: 8.76 | +31: iteration 9850/ 37905 | consumed samples: 2521600 | consumed tokens: 5164236800 | elapsed time per iteration (s): 0.18 | learning rate: 1.716E-04 | global batch size: 256 | lm loss: 3.076677E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1444.838 | TFLOPs: 9.20 | +31: iteration 9860/ 37905 | consumed samples: 2524160 | consumed tokens: 5169479680 | elapsed time per iteration (s): 0.19 | learning rate: 1.716E-04 | global batch size: 256 | lm loss: 3.096696E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.400 | TFLOPs: 8.49 | +31: iteration 9870/ 37905 | consumed samples: 2526720 | consumed tokens: 5174722560 | elapsed time per iteration (s): 0.19 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.029025E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.337 | TFLOPs: 8.45 | +31: iteration 9880/ 37905 | consumed samples: 2529280 | consumed tokens: 5179965440 | elapsed time per iteration (s): 0.21 | learning rate: 1.715E-04 | global batch size: 256 | lm loss: 3.061718E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.228 | TFLOPs: 7.68 | +31: iteration 9890/ 37905 | consumed samples: 2531840 | consumed tokens: 5185208320 | elapsed time per iteration (s): 0.18 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 3.100883E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1386.782 | TFLOPs: 8.83 | +31: iteration 9900/ 37905 | consumed samples: 2534400 | consumed tokens: 5190451200 | elapsed time per iteration (s): 0.20 | learning rate: 1.714E-04 | global batch size: 256 | lm loss: 3.102051E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.697 | TFLOPs: 8.11 | +31: iteration 9910/ 37905 | consumed samples: 2536960 | consumed tokens: 5195694080 | elapsed time per iteration (s): 0.20 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.077575E+00 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.068 | TFLOPs: 8.10 | +31: iteration 9920/ 37905 | consumed samples: 2539520 | consumed tokens: 5200936960 | elapsed time per iteration (s): 0.19 | learning rate: 1.713E-04 | global batch size: 256 | lm loss: 3.105419E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.880 | TFLOPs: 8.48 | +31: iteration 9930/ 37905 | consumed samples: 2542080 | consumed tokens: 5206179840 | elapsed time per iteration (s): 0.20 | learning rate: 1.712E-04 | global batch size: 256 | lm loss: 3.077755E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.502 | TFLOPs: 8.05 | +31: iteration 9940/ 37905 | consumed samples: 2544640 | consumed tokens: 5211422720 | elapsed time per iteration (s): 0.17 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 3.046092E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1463.280 | TFLOPs: 9.32 | +31: iteration 9950/ 37905 | consumed samples: 2547200 | consumed tokens: 5216665600 | elapsed time per iteration (s): 0.19 | learning rate: 1.711E-04 | global batch size: 256 | lm loss: 3.039627E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1332.004 | TFLOPs: 8.48 | +31: iteration 9960/ 37905 | consumed samples: 2549760 | consumed tokens: 5221908480 | elapsed time per iteration (s): 0.21 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 3.083614E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.110 | TFLOPs: 7.72 | +31: iteration 9970/ 37905 | consumed samples: 2552320 | consumed tokens: 5227151360 | elapsed time per iteration (s): 0.20 | learning rate: 1.710E-04 | global batch size: 256 | lm loss: 3.035408E+00 | grad norm: 0.343 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1276.777 | TFLOPs: 8.13 | +31: iteration 9980/ 37905 | consumed samples: 2554880 | consumed tokens: 5232394240 | elapsed time per iteration (s): 0.20 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 3.090551E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1300.711 | TFLOPs: 8.28 | +31: iteration 9990/ 37905 | consumed samples: 2557440 | consumed tokens: 5237637120 | elapsed time per iteration (s): 0.19 | learning rate: 1.709E-04 | global batch size: 256 | lm loss: 3.090890E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.736 | TFLOPs: 8.45 | + 0: [2022-11-24 14:47:22,391] [INFO] [logging.py:68:log_dist] [Rank 0] step=10000, skipped=0, lr=[0.00017081813074702097, 0.00017081813074702097, 0.00017081813074702097], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 10000/ 37905 | consumed samples: 2560000 | consumed tokens: 5242880000 | elapsed time per iteration (s): 0.18 | learning rate: 1.708E-04 | global batch size: 256 | lm loss: 3.089893E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1397.194 | TFLOPs: 8.90 | + 0: steps: 10000 loss: 3.0666 iter time (s): 0.195 samples/sec: 1314.672 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 10000 | lm loss value: 2.931548E+00 | lm loss PPL: 1.875664E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 10000 to checkpoints_83m + 0: [2022-11-24 14:47:22,473] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step10000 is begin to save! + 0: [2022-11-24 14:47:22,482] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,579] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,601] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,612] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,623] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,634] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,666] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:47:22,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:47:22,668] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step10000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:47:22,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:47:22,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:47:22,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:47:22,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:47:22,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +31: [2022-11-24 14:47:22,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +15: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:47:22,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:47:22,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +28: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:47:22,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +28: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:47:22,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-24 14:47:22,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:47:22,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-24 14:47:22,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-24 14:47:22,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:47:22,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-24 14:47:22,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +30: [2022-11-24 14:47:22,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-24 14:47:22,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:47:22,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:47:22,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:47:22,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-24 14:47:22,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-24 14:47:22,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:47:22,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +21: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:47:22,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-24 14:47:22,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-24 14:47:22,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-24 14:47:22,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +15: [2022-11-24 14:47:22,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +31: [2022-11-24 14:47:22,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +13: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:47:22,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:47:22,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-24 14:47:22,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-24 14:47:22,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:47:22,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-24 14:47:22,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:47:22,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-24 14:47:22,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:47:22,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-24 14:47:22,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-24 14:47:22,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:47:22,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 14:47:22,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 14:47:22,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:47:22,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +24: [2022-11-24 14:47:22,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-24 14:47:22,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:47:22,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-24 14:47:22,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:47:22,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:47:22,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +21: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:47:22,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-24 14:47:22,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-24 14:47:22,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +16: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-24 14:47:22,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:47:22,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:47:22,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:47:22,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:47:22,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-24 14:47:22,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:47:22,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:47:22,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:47:22,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:47:22,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-24 14:47:22,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-24 14:47:22,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:47:22,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:47:22,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-24 14:47:22,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 14:47:22,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:47:22,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-24 14:47:22,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 14:47:22,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-24 14:47:22,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:47:22,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:47:22,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:47:22,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 3: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-24 14:47:22,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:47:22,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-24 14:47:22,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:47:22,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-24 14:47:22,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-24 14:47:22,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 2: [2022-11-24 14:47:22,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:47:22,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +30: [2022-11-24 14:47:22,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +19: [2022-11-24 14:47:22,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:47:22,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:47:22,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-24 14:47:22,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:47:22,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 14:47:22,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:47:22,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:47:22,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:47:22,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:47:22,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +15: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +27: [2022-11-24 14:47:22,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +22: [2022-11-24 14:47:22,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 14:47:22,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +31: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +21: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +23: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +18: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 8: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +26: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +13: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +18: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +14: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 6: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +13: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +21: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +10: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +30: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +14: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +26: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +23: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +17: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +11: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +12: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +27: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +10: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +30: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +16: [2022-11-24 14:47:22,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 4: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +20: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +17: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +11: [2022-11-24 14:47:22,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 9: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +12: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +20: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +21: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 7: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +25: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +19: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +28: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +25: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 1: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 5: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +24: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +28: [2022-11-24 14:47:22,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +29: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +29: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +28: [2022-11-24 14:47:22,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! +15: [2022-11-24 14:47:22,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:47:22,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step10000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 14:47:22,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step10000 is ready now! + 0: successfully saved checkpoint at iteration 10000 to checkpoints_83m +31: time (ms) | save-checkpoint: 322.90 +31: iteration 10010/ 37905 | consumed samples: 2562560 | consumed tokens: 5248122880 | elapsed time per iteration (s): 0.25 | learning rate: 1.708E-04 | global batch size: 256 | lm loss: 3.057444E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.269 | TFLOPs: 6.63 | +31: iteration 10020/ 37905 | consumed samples: 2565120 | consumed tokens: 5253365760 | elapsed time per iteration (s): 0.20 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.085575E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1301.416 | TFLOPs: 8.29 | +31: iteration 10030/ 37905 | consumed samples: 2567680 | consumed tokens: 5258608640 | elapsed time per iteration (s): 0.20 | learning rate: 1.707E-04 | global batch size: 256 | lm loss: 3.088974E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.988 | TFLOPs: 8.26 | +31: iteration 10040/ 37905 | consumed samples: 2570240 | consumed tokens: 5263851520 | elapsed time per iteration (s): 0.19 | learning rate: 1.706E-04 | global batch size: 256 | lm loss: 3.090582E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.407 | TFLOPs: 8.47 | +31: iteration 10050/ 37905 | consumed samples: 2572800 | consumed tokens: 5269094400 | elapsed time per iteration (s): 0.22 | learning rate: 1.705E-04 | global batch size: 256 | lm loss: 3.061304E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.943 | TFLOPs: 7.41 | +31: iteration 10060/ 37905 | consumed samples: 2575360 | consumed tokens: 5274337280 | elapsed time per iteration (s): 0.19 | learning rate: 1.705E-04 | global batch size: 256 | lm loss: 3.068307E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1349.602 | TFLOPs: 8.60 | +31: iteration 10070/ 37905 | consumed samples: 2577920 | consumed tokens: 5279580160 | elapsed time per iteration (s): 0.19 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.075643E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1322.632 | TFLOPs: 8.42 | +31: iteration 10080/ 37905 | consumed samples: 2580480 | consumed tokens: 5284823040 | elapsed time per iteration (s): 0.18 | learning rate: 1.704E-04 | global batch size: 256 | lm loss: 3.029333E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1445.403 | TFLOPs: 9.21 | +31: iteration 10090/ 37905 | consumed samples: 2583040 | consumed tokens: 5290065920 | elapsed time per iteration (s): 0.22 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 3.043621E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.688 | TFLOPs: 7.37 | +31: iteration 10100/ 37905 | consumed samples: 2585600 | consumed tokens: 5295308800 | elapsed time per iteration (s): 0.18 | learning rate: 1.703E-04 | global batch size: 256 | lm loss: 3.079148E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1461.748 | TFLOPs: 9.31 | +31: iteration 10110/ 37905 | consumed samples: 2588160 | consumed tokens: 5300551680 | elapsed time per iteration (s): 0.18 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 3.050208E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1390.133 | TFLOPs: 8.85 | +31: iteration 10120/ 37905 | consumed samples: 2590720 | consumed tokens: 5305794560 | elapsed time per iteration (s): 0.18 | learning rate: 1.702E-04 | global batch size: 256 | lm loss: 3.034398E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1391.160 | TFLOPs: 8.86 | +31: iteration 10130/ 37905 | consumed samples: 2593280 | consumed tokens: 5311037440 | elapsed time per iteration (s): 0.21 | learning rate: 1.701E-04 | global batch size: 256 | lm loss: 3.062825E+00 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.006 | TFLOPs: 7.78 | +31: iteration 10140/ 37905 | consumed samples: 2595840 | consumed tokens: 5316280320 | elapsed time per iteration (s): 0.19 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 3.073437E+00 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.399 | TFLOPs: 8.39 | +31: iteration 10150/ 37905 | consumed samples: 2598400 | consumed tokens: 5321523200 | elapsed time per iteration (s): 0.20 | learning rate: 1.700E-04 | global batch size: 256 | lm loss: 3.044724E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.239 | TFLOPs: 7.98 | +31: iteration 10160/ 37905 | consumed samples: 2600960 | consumed tokens: 5326766080 | elapsed time per iteration (s): 0.18 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 3.061370E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1397.277 | TFLOPs: 8.90 | +31: iteration 10170/ 37905 | consumed samples: 2603520 | consumed tokens: 5332008960 | elapsed time per iteration (s): 0.20 | learning rate: 1.699E-04 | global batch size: 256 | lm loss: 3.085532E+00 | grad norm: 0.336 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1300.194 | TFLOPs: 8.28 | +31: iteration 10180/ 37905 | consumed samples: 2606080 | consumed tokens: 5337251840 | elapsed time per iteration (s): 0.19 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 3.058668E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1373.962 | TFLOPs: 8.75 | +31: iteration 10190/ 37905 | consumed samples: 2608640 | consumed tokens: 5342494720 | elapsed time per iteration (s): 0.19 | learning rate: 1.698E-04 | global batch size: 256 | lm loss: 3.070045E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.114 | TFLOPs: 8.45 | +31: iteration 10200/ 37905 | consumed samples: 2611200 | consumed tokens: 5347737600 | elapsed time per iteration (s): 0.19 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 3.057690E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.646 | TFLOPs: 8.78 | +31: iteration 10210/ 37905 | consumed samples: 2613760 | consumed tokens: 5352980480 | elapsed time per iteration (s): 0.21 | learning rate: 1.697E-04 | global batch size: 256 | lm loss: 3.059118E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.624 | TFLOPs: 7.89 | +31: iteration 10220/ 37905 | consumed samples: 2616320 | consumed tokens: 5358223360 | elapsed time per iteration (s): 0.19 | learning rate: 1.696E-04 | global batch size: 256 | lm loss: 3.042579E+00 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1329.922 | TFLOPs: 8.47 | +31: iteration 10230/ 37905 | consumed samples: 2618880 | consumed tokens: 5363466240 | elapsed time per iteration (s): 0.20 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 3.058862E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.968 | TFLOPs: 7.99 | +31: iteration 10240/ 37905 | consumed samples: 2621440 | consumed tokens: 5368709120 | elapsed time per iteration (s): 0.19 | learning rate: 1.695E-04 | global batch size: 256 | lm loss: 3.075582E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1377.819 | TFLOPs: 8.78 | +31: iteration 10250/ 37905 | consumed samples: 2624000 | consumed tokens: 5373952000 | elapsed time per iteration (s): 0.21 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.057803E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.852 | TFLOPs: 7.90 | +31: iteration 10260/ 37905 | consumed samples: 2626560 | consumed tokens: 5379194880 | elapsed time per iteration (s): 0.20 | learning rate: 1.694E-04 | global batch size: 256 | lm loss: 3.026457E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1268.300 | TFLOPs: 8.08 | +31: iteration 10270/ 37905 | consumed samples: 2629120 | consumed tokens: 5384437760 | elapsed time per iteration (s): 0.19 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 3.058984E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1314.417 | TFLOPs: 8.37 | +31: iteration 10280/ 37905 | consumed samples: 2631680 | consumed tokens: 5389680640 | elapsed time per iteration (s): 0.21 | learning rate: 1.693E-04 | global batch size: 256 | lm loss: 3.071046E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.455 | TFLOPs: 7.64 | +31: iteration 10290/ 37905 | consumed samples: 2634240 | consumed tokens: 5394923520 | elapsed time per iteration (s): 0.19 | learning rate: 1.692E-04 | global batch size: 256 | lm loss: 3.084579E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.712 | TFLOPs: 8.40 | +31: iteration 10300/ 37905 | consumed samples: 2636800 | consumed tokens: 5400166400 | elapsed time per iteration (s): 0.21 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 3.034108E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.077 | TFLOPs: 7.78 | +31: iteration 10310/ 37905 | consumed samples: 2639360 | consumed tokens: 5405409280 | elapsed time per iteration (s): 0.17 | learning rate: 1.691E-04 | global batch size: 256 | lm loss: 3.070153E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1479.742 | TFLOPs: 9.42 | +31: iteration 10320/ 37905 | consumed samples: 2641920 | consumed tokens: 5410652160 | elapsed time per iteration (s): 0.19 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.092069E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.602 | TFLOPs: 8.54 | +31: iteration 10330/ 37905 | consumed samples: 2644480 | consumed tokens: 5415895040 | elapsed time per iteration (s): 0.18 | learning rate: 1.690E-04 | global batch size: 256 | lm loss: 3.045163E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.478 | TFLOPs: 8.97 | +31: iteration 10340/ 37905 | consumed samples: 2647040 | consumed tokens: 5421137920 | elapsed time per iteration (s): 0.17 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 3.091233E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1465.824 | TFLOPs: 9.34 | +31: iteration 10350/ 37905 | consumed samples: 2649600 | consumed tokens: 5426380800 | elapsed time per iteration (s): 0.18 | learning rate: 1.689E-04 | global batch size: 256 | lm loss: 3.060020E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.780 | TFLOPs: 8.93 | +31: iteration 10360/ 37905 | consumed samples: 2652160 | consumed tokens: 5431623680 | elapsed time per iteration (s): 0.20 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 3.068669E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1299.858 | TFLOPs: 8.28 | +31: iteration 10370/ 37905 | consumed samples: 2654720 | consumed tokens: 5436866560 | elapsed time per iteration (s): 0.18 | learning rate: 1.688E-04 | global batch size: 256 | lm loss: 3.059907E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.490 | TFLOPs: 8.97 | +31: iteration 10380/ 37905 | consumed samples: 2657280 | consumed tokens: 5442109440 | elapsed time per iteration (s): 0.18 | learning rate: 1.687E-04 | global batch size: 256 | lm loss: 3.051395E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1432.978 | TFLOPs: 9.13 | +31: iteration 10390/ 37905 | consumed samples: 2659840 | consumed tokens: 5447352320 | elapsed time per iteration (s): 0.20 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 3.045630E+00 | grad norm: 0.419 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.458 | TFLOPs: 8.11 | +31: iteration 10400/ 37905 | consumed samples: 2662400 | consumed tokens: 5452595200 | elapsed time per iteration (s): 0.18 | learning rate: 1.686E-04 | global batch size: 256 | lm loss: 3.065473E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1404.063 | TFLOPs: 8.94 | +31: iteration 10410/ 37905 | consumed samples: 2664960 | consumed tokens: 5457838080 | elapsed time per iteration (s): 0.19 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 3.045843E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.921 | TFLOPs: 8.76 | +31: iteration 10420/ 37905 | consumed samples: 2667520 | consumed tokens: 5463080960 | elapsed time per iteration (s): 0.21 | learning rate: 1.685E-04 | global batch size: 256 | lm loss: 3.070588E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.254 | TFLOPs: 7.92 | +31: iteration 10430/ 37905 | consumed samples: 2670080 | consumed tokens: 5468323840 | elapsed time per iteration (s): 0.19 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 3.067563E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.763 | TFLOPs: 8.55 | +31: iteration 10440/ 37905 | consumed samples: 2672640 | consumed tokens: 5473566720 | elapsed time per iteration (s): 0.20 | learning rate: 1.684E-04 | global batch size: 256 | lm loss: 3.056024E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.828 | TFLOPs: 8.31 | +31: iteration 10450/ 37905 | consumed samples: 2675200 | consumed tokens: 5478809600 | elapsed time per iteration (s): 0.19 | learning rate: 1.683E-04 | global batch size: 256 | lm loss: 3.045939E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.664 | TFLOPs: 8.54 | +31: iteration 10460/ 37905 | consumed samples: 2677760 | consumed tokens: 5484052480 | elapsed time per iteration (s): 0.19 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 3.053615E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.200 | TFLOPs: 8.45 | +31: iteration 10470/ 37905 | consumed samples: 2680320 | consumed tokens: 5489295360 | elapsed time per iteration (s): 0.19 | learning rate: 1.682E-04 | global batch size: 256 | lm loss: 3.061489E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1371.330 | TFLOPs: 8.73 | +31: iteration 10480/ 37905 | consumed samples: 2682880 | consumed tokens: 5494538240 | elapsed time per iteration (s): 0.21 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 3.049439E+00 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.117 | TFLOPs: 7.67 | +31: iteration 10490/ 37905 | consumed samples: 2685440 | consumed tokens: 5499781120 | elapsed time per iteration (s): 0.19 | learning rate: 1.681E-04 | global batch size: 256 | lm loss: 3.044927E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.130 | TFLOPs: 8.45 | +31: iteration 10500/ 37905 | consumed samples: 2688000 | consumed tokens: 5505024000 | elapsed time per iteration (s): 0.18 | learning rate: 1.680E-04 | global batch size: 256 | lm loss: 3.052047E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1398.434 | TFLOPs: 8.91 | +31: iteration 10510/ 37905 | consumed samples: 2690560 | consumed tokens: 5510266880 | elapsed time per iteration (s): 0.19 | learning rate: 1.680E-04 | global batch size: 256 | lm loss: 3.069503E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.247 | TFLOPs: 8.55 | +31: iteration 10520/ 37905 | consumed samples: 2693120 | consumed tokens: 5515509760 | elapsed time per iteration (s): 0.21 | learning rate: 1.679E-04 | global batch size: 256 | lm loss: 3.105421E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1214.585 | TFLOPs: 7.74 | +31: iteration 10530/ 37905 | consumed samples: 2695680 | consumed tokens: 5520752640 | elapsed time per iteration (s): 0.20 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 3.052514E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.836 | TFLOPs: 8.10 | +31: iteration 10540/ 37905 | consumed samples: 2698240 | consumed tokens: 5525995520 | elapsed time per iteration (s): 0.17 | learning rate: 1.678E-04 | global batch size: 256 | lm loss: 3.050018E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1476.091 | TFLOPs: 9.40 | +31: iteration 10550/ 37905 | consumed samples: 2700800 | consumed tokens: 5531238400 | elapsed time per iteration (s): 0.19 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 3.033373E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1355.125 | TFLOPs: 8.63 | +31: iteration 10560/ 37905 | consumed samples: 2703360 | consumed tokens: 5536481280 | elapsed time per iteration (s): 0.19 | learning rate: 1.677E-04 | global batch size: 256 | lm loss: 3.042454E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.970 | TFLOPs: 8.57 | +31: iteration 10570/ 37905 | consumed samples: 2705920 | consumed tokens: 5541724160 | elapsed time per iteration (s): 0.17 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 3.041927E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1480.648 | TFLOPs: 9.43 | +31: iteration 10580/ 37905 | consumed samples: 2708480 | consumed tokens: 5546967040 | elapsed time per iteration (s): 0.18 | learning rate: 1.676E-04 | global batch size: 256 | lm loss: 3.047897E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1400.348 | TFLOPs: 8.92 | +31: iteration 10590/ 37905 | consumed samples: 2711040 | consumed tokens: 5552209920 | elapsed time per iteration (s): 0.21 | learning rate: 1.675E-04 | global batch size: 256 | lm loss: 3.087672E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.067 | TFLOPs: 7.69 | +31: iteration 10600/ 37905 | consumed samples: 2713600 | consumed tokens: 5557452800 | elapsed time per iteration (s): 0.18 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 3.038177E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1394.255 | TFLOPs: 8.88 | +31: iteration 10610/ 37905 | consumed samples: 2716160 | consumed tokens: 5562695680 | elapsed time per iteration (s): 0.19 | learning rate: 1.674E-04 | global batch size: 256 | lm loss: 3.021881E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.600 | TFLOPs: 8.37 | +31: iteration 10620/ 37905 | consumed samples: 2718720 | consumed tokens: 5567938560 | elapsed time per iteration (s): 0.19 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.042310E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1334.165 | TFLOPs: 8.50 | +31: iteration 10630/ 37905 | consumed samples: 2721280 | consumed tokens: 5573181440 | elapsed time per iteration (s): 0.19 | learning rate: 1.673E-04 | global batch size: 256 | lm loss: 3.022876E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.663 | TFLOPs: 8.58 | +31: iteration 10640/ 37905 | consumed samples: 2723840 | consumed tokens: 5578424320 | elapsed time per iteration (s): 0.18 | learning rate: 1.672E-04 | global batch size: 256 | lm loss: 3.054632E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1409.396 | TFLOPs: 8.98 | +31: iteration 10650/ 37905 | consumed samples: 2726400 | consumed tokens: 5583667200 | elapsed time per iteration (s): 0.19 | learning rate: 1.672E-04 | global batch size: 256 | lm loss: 3.061910E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.202 | TFLOPs: 8.57 | +31: iteration 10660/ 37905 | consumed samples: 2728960 | consumed tokens: 5588910080 | elapsed time per iteration (s): 0.20 | learning rate: 1.671E-04 | global batch size: 256 | lm loss: 3.059457E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.689 | TFLOPs: 8.02 | +31: iteration 10670/ 37905 | consumed samples: 2731520 | consumed tokens: 5594152960 | elapsed time per iteration (s): 0.20 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 3.075492E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.077 | TFLOPs: 7.97 | +31: iteration 10680/ 37905 | consumed samples: 2734080 | consumed tokens: 5599395840 | elapsed time per iteration (s): 0.20 | learning rate: 1.670E-04 | global batch size: 256 | lm loss: 3.049875E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.191 | TFLOPs: 7.97 | +31: iteration 10690/ 37905 | consumed samples: 2736640 | consumed tokens: 5604638720 | elapsed time per iteration (s): 0.22 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 3.061897E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.982 | TFLOPs: 7.53 | +31: iteration 10700/ 37905 | consumed samples: 2739200 | consumed tokens: 5609881600 | elapsed time per iteration (s): 0.20 | learning rate: 1.669E-04 | global batch size: 256 | lm loss: 3.045699E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.540 | TFLOPs: 8.33 | +31: iteration 10710/ 37905 | consumed samples: 2741760 | consumed tokens: 5615124480 | elapsed time per iteration (s): 0.19 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 3.070891E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.603 | TFLOPs: 8.54 | +31: iteration 10720/ 37905 | consumed samples: 2744320 | consumed tokens: 5620367360 | elapsed time per iteration (s): 0.19 | learning rate: 1.668E-04 | global batch size: 256 | lm loss: 3.081136E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1380.484 | TFLOPs: 8.79 | +31: iteration 10730/ 37905 | consumed samples: 2746880 | consumed tokens: 5625610240 | elapsed time per iteration (s): 0.18 | learning rate: 1.667E-04 | global batch size: 256 | lm loss: 3.043791E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1389.302 | TFLOPs: 8.85 | +31: iteration 10740/ 37905 | consumed samples: 2749440 | consumed tokens: 5630853120 | elapsed time per iteration (s): 0.18 | learning rate: 1.666E-04 | global batch size: 256 | lm loss: 3.020374E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1387.868 | TFLOPs: 8.84 | +31: iteration 10750/ 37905 | consumed samples: 2752000 | consumed tokens: 5636096000 | elapsed time per iteration (s): 0.20 | learning rate: 1.666E-04 | global batch size: 256 | lm loss: 3.047544E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1298.423 | TFLOPs: 8.27 | +31: iteration 10760/ 37905 | consumed samples: 2754560 | consumed tokens: 5641338880 | elapsed time per iteration (s): 0.19 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 3.056494E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1332.021 | TFLOPs: 8.48 | +31: iteration 10770/ 37905 | consumed samples: 2757120 | consumed tokens: 5646581760 | elapsed time per iteration (s): 0.20 | learning rate: 1.665E-04 | global batch size: 256 | lm loss: 3.016609E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1303.093 | TFLOPs: 8.30 | +31: iteration 10780/ 37905 | consumed samples: 2759680 | consumed tokens: 5651824640 | elapsed time per iteration (s): 0.20 | learning rate: 1.664E-04 | global batch size: 256 | lm loss: 3.003201E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1268.318 | TFLOPs: 8.08 | +31: iteration 10790/ 37905 | consumed samples: 2762240 | consumed tokens: 5657067520 | elapsed time per iteration (s): 0.22 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 3.062484E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.878 | TFLOPs: 7.55 | +31: iteration 10800/ 37905 | consumed samples: 2764800 | consumed tokens: 5662310400 | elapsed time per iteration (s): 0.20 | learning rate: 1.663E-04 | global batch size: 256 | lm loss: 3.021509E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.298 | TFLOPs: 8.19 | +31: iteration 10810/ 37905 | consumed samples: 2767360 | consumed tokens: 5667553280 | elapsed time per iteration (s): 0.22 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 3.031017E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.806 | TFLOPs: 7.40 | +31: iteration 10820/ 37905 | consumed samples: 2769920 | consumed tokens: 5672796160 | elapsed time per iteration (s): 0.17 | learning rate: 1.662E-04 | global batch size: 256 | lm loss: 3.040084E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1485.132 | TFLOPs: 9.46 | +31: iteration 10830/ 37905 | consumed samples: 2772480 | consumed tokens: 5678039040 | elapsed time per iteration (s): 0.21 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 3.050357E+00 | grad norm: 0.350 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.407 | TFLOPs: 7.64 | +31: iteration 10840/ 37905 | consumed samples: 2775040 | consumed tokens: 5683281920 | elapsed time per iteration (s): 0.21 | learning rate: 1.661E-04 | global batch size: 256 | lm loss: 3.041544E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.275 | TFLOPs: 7.82 | +31: iteration 10850/ 37905 | consumed samples: 2777600 | consumed tokens: 5688524800 | elapsed time per iteration (s): 0.23 | learning rate: 1.660E-04 | global batch size: 256 | lm loss: 3.001774E+00 | grad norm: 0.322 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.541 | TFLOPs: 7.14 | +31: iteration 10860/ 37905 | consumed samples: 2780160 | consumed tokens: 5693767680 | elapsed time per iteration (s): 0.23 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 3.079138E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.389 | TFLOPs: 7.22 | +31: iteration 10870/ 37905 | consumed samples: 2782720 | consumed tokens: 5699010560 | elapsed time per iteration (s): 0.19 | learning rate: 1.659E-04 | global batch size: 256 | lm loss: 3.049212E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.340 | TFLOPs: 8.44 | +31: iteration 10880/ 37905 | consumed samples: 2785280 | consumed tokens: 5704253440 | elapsed time per iteration (s): 0.19 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 3.067488E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1373.461 | TFLOPs: 8.75 | +31: iteration 10890/ 37905 | consumed samples: 2787840 | consumed tokens: 5709496320 | elapsed time per iteration (s): 0.20 | learning rate: 1.658E-04 | global batch size: 256 | lm loss: 3.046624E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1276.478 | TFLOPs: 8.13 | +31: iteration 10900/ 37905 | consumed samples: 2790400 | consumed tokens: 5714739200 | elapsed time per iteration (s): 0.20 | learning rate: 1.657E-04 | global batch size: 256 | lm loss: 3.033976E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.700 | TFLOPs: 8.09 | +31: iteration 10910/ 37905 | consumed samples: 2792960 | consumed tokens: 5719982080 | elapsed time per iteration (s): 0.18 | learning rate: 1.656E-04 | global batch size: 256 | lm loss: 3.074128E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1392.014 | TFLOPs: 8.87 | +31: iteration 10920/ 37905 | consumed samples: 2795520 | consumed tokens: 5725224960 | elapsed time per iteration (s): 0.19 | learning rate: 1.656E-04 | global batch size: 256 | lm loss: 3.016590E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.771 | TFLOPs: 8.45 | +31: iteration 10930/ 37905 | consumed samples: 2798080 | consumed tokens: 5730467840 | elapsed time per iteration (s): 0.19 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 3.028925E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1337.588 | TFLOPs: 8.52 | +31: iteration 10940/ 37905 | consumed samples: 2800640 | consumed tokens: 5735710720 | elapsed time per iteration (s): 0.20 | learning rate: 1.655E-04 | global batch size: 256 | lm loss: 2.996055E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.924 | TFLOPs: 8.33 | +31: iteration 10950/ 37905 | consumed samples: 2803200 | consumed tokens: 5740953600 | elapsed time per iteration (s): 0.20 | learning rate: 1.654E-04 | global batch size: 256 | lm loss: 3.062939E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.078 | TFLOPs: 7.99 | +31: iteration 10960/ 37905 | consumed samples: 2805760 | consumed tokens: 5746196480 | elapsed time per iteration (s): 0.20 | learning rate: 1.654E-04 | global batch size: 256 | lm loss: 3.031700E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.976 | TFLOPs: 8.11 | +31: iteration 10970/ 37905 | consumed samples: 2808320 | consumed tokens: 5751439360 | elapsed time per iteration (s): 0.20 | learning rate: 1.653E-04 | global batch size: 256 | lm loss: 3.038051E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.071 | TFLOPs: 8.22 | +31: iteration 10980/ 37905 | consumed samples: 2810880 | consumed tokens: 5756682240 | elapsed time per iteration (s): 0.22 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 3.037432E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.721 | TFLOPs: 7.33 | +31: iteration 10990/ 37905 | consumed samples: 2813440 | consumed tokens: 5761925120 | elapsed time per iteration (s): 0.21 | learning rate: 1.652E-04 | global batch size: 256 | lm loss: 3.045030E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.993 | TFLOPs: 7.88 | +31: iteration 11000/ 37905 | consumed samples: 2816000 | consumed tokens: 5767168000 | elapsed time per iteration (s): 0.20 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.044650E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.747 | TFLOPs: 8.10 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 11000 | lm loss value: 2.931354E+00 | lm loss PPL: 1.875301E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 11000 to checkpoints_83m + 0: [2022-11-24 14:50:38,442] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step11000 is begin to save! + 0: [2022-11-24 14:50:38,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,535] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,579] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,590] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,611] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,622] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,633] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:50:38,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:50:38,635] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step11000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:50:38,635] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:50:38,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:50:38,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:50:38,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +20: [2022-11-24 14:50:38,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:50:38,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 9: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +14: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 5: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 5: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +18: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +10: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +30: [2022-11-24 14:50:38,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:50:38,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +21: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +19: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 4: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +26: [2022-11-24 14:50:38,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +13: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +28: [2022-11-24 14:50:38,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +17: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +25: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:50:38,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:50:38,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:50:38,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:50:38,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 9: [2022-11-24 14:50:38,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:50:38,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:50:38,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:50:38,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:50:38,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:50:38,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +10: [2022-11-24 14:50:38,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:50:38,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:50:38,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:50:38,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +13: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 4: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +30: [2022-11-24 14:50:38,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +26: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:50:38,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:50:38,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +18: [2022-11-24 14:50:38,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +19: [2022-11-24 14:50:38,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +28: [2022-11-24 14:50:38,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:50:38,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +25: [2022-11-24 14:50:38,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +21: [2022-11-24 14:50:38,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:50:38,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:50:38,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 9: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +20: [2022-11-24 14:50:38,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:50:38,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:50:38,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:50:38,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:50:38,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:50:38,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:50:38,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +10: [2022-11-24 14:50:38,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:50:38,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 14:50:38,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +30: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:50:38,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 4: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +13: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +26: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:50:38,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:50:38,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +19: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +19: [2022-11-24 14:50:38,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +18: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:50:38,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +25: [2022-11-24 14:50:38,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +21: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 14:50:38,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:50:38,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +20: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 9: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:50:38,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:50:38,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:50:38,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:50:38,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +14: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:50:38,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:50:38,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +10: [2022-11-24 14:50:38,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +10: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:50:38,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 4: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +30: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +13: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +26: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:50:38,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +17: [2022-11-24 14:50:38,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +19: [2022-11-24 14:50:38,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 14:50:38,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:50:38,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 14:50:38,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +18: [2022-11-24 14:50:38,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +25: [2022-11-24 14:50:38,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +21: [2022-11-24 14:50:38,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:50:38,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 9: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:50:38,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +20: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:50:38,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:50:38,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:50:38,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:50:38,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 5: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:50:38,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +10: [2022-11-24 14:50:38,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 14:50:38,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:50:38,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +30: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:50:38,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +13: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 4: [2022-11-24 14:50:38,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:50:38,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +19: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +26: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:50:38,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +18: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +25: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:50:38,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +21: [2022-11-24 14:50:38,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:50:38,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 9: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:50:38,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +20: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:50:38,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:50:38,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:50:38,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:50:38,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:50:38,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 5: [2022-11-24 14:50:38,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:50:38,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +10: [2022-11-24 14:50:38,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +10: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +30: [2022-11-24 14:50:38,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 14:50:38,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +13: [2022-11-24 14:50:38,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 4: [2022-11-24 14:50:38,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:50:38,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +17: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +26: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +19: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +18: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +28: [2022-11-24 14:50:38,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:50:38,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:50:38,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:50:38,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +21: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 9: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:50:38,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:50:38,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +20: [2022-11-24 14:50:38,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:50:38,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:50:38,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:50:38,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:50:38,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:50:38,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +16: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:50:38,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 5: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +30: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +22: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +12: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +22: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +14: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +21: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 5: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +14: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +12: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 4: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +19: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 2: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 3: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 6: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 8: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +13: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +26: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +21: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +17: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +29: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +10: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +16: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +19: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +13: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +26: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +24: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +23: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +18: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +25: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +10: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +15: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:50:38,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +23: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +29: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +28: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:50:38,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +24: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +11: [2022-11-24 14:50:38,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +31: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +27: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 1: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +20: [2022-11-24 14:50:38,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +15: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +17: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +11: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +31: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +27: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! +25: [2022-11-24 14:50:38,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +20: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step11000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +25: [2022-11-24 14:50:38,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 7: [2022-11-24 14:50:38,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step11000 is ready now! + 0: successfully saved checkpoint at iteration 11000 to checkpoints_83m +31: time (ms) | save-checkpoint: 316.96 +31: iteration 11010/ 37905 | consumed samples: 2818560 | consumed tokens: 5772410880 | elapsed time per iteration (s): 0.23 | learning rate: 1.651E-04 | global batch size: 256 | lm loss: 3.022594E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.395 | TFLOPs: 7.14 | +31: iteration 11020/ 37905 | consumed samples: 2821120 | consumed tokens: 5777653760 | elapsed time per iteration (s): 0.20 | learning rate: 1.650E-04 | global batch size: 256 | lm loss: 3.084874E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.867 | TFLOPs: 8.02 | +31: iteration 11030/ 37905 | consumed samples: 2823680 | consumed tokens: 5782896640 | elapsed time per iteration (s): 0.20 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.006458E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.713 | TFLOPs: 7.98 | +31: iteration 11040/ 37905 | consumed samples: 2826240 | consumed tokens: 5788139520 | elapsed time per iteration (s): 0.19 | learning rate: 1.649E-04 | global batch size: 256 | lm loss: 3.043143E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1371.448 | TFLOPs: 8.73 | +31: iteration 11050/ 37905 | consumed samples: 2828800 | consumed tokens: 5793382400 | elapsed time per iteration (s): 0.20 | learning rate: 1.648E-04 | global batch size: 256 | lm loss: 3.054298E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.933 | TFLOPs: 8.02 | +31: iteration 11060/ 37905 | consumed samples: 2831360 | consumed tokens: 5798625280 | elapsed time per iteration (s): 0.20 | learning rate: 1.648E-04 | global batch size: 256 | lm loss: 3.013428E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.047 | TFLOPs: 8.24 | +31: iteration 11070/ 37905 | consumed samples: 2833920 | consumed tokens: 5803868160 | elapsed time per iteration (s): 0.22 | learning rate: 1.647E-04 | global batch size: 256 | lm loss: 3.031638E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.595 | TFLOPs: 7.47 | +31: iteration 11080/ 37905 | consumed samples: 2836480 | consumed tokens: 5809111040 | elapsed time per iteration (s): 0.20 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 3.051720E+00 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.790 | TFLOPs: 7.97 | +31: iteration 11090/ 37905 | consumed samples: 2839040 | consumed tokens: 5814353920 | elapsed time per iteration (s): 0.22 | learning rate: 1.646E-04 | global batch size: 256 | lm loss: 3.027666E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.377 | TFLOPs: 7.28 | +31: iteration 11100/ 37905 | consumed samples: 2841600 | consumed tokens: 5819596800 | elapsed time per iteration (s): 0.20 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 3.055982E+00 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.595 | TFLOPs: 8.35 | +31: iteration 11110/ 37905 | consumed samples: 2844160 | consumed tokens: 5824839680 | elapsed time per iteration (s): 0.20 | learning rate: 1.645E-04 | global batch size: 256 | lm loss: 3.068267E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1291.159 | TFLOPs: 8.22 | +31: iteration 11120/ 37905 | consumed samples: 2846720 | consumed tokens: 5830082560 | elapsed time per iteration (s): 0.20 | learning rate: 1.644E-04 | global batch size: 256 | lm loss: 3.051647E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1257.608 | TFLOPs: 8.01 | +31: iteration 11130/ 37905 | consumed samples: 2849280 | consumed tokens: 5835325440 | elapsed time per iteration (s): 0.21 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.013352E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.565 | TFLOPs: 7.69 | +31: iteration 11140/ 37905 | consumed samples: 2851840 | consumed tokens: 5840568320 | elapsed time per iteration (s): 0.19 | learning rate: 1.643E-04 | global batch size: 256 | lm loss: 3.043562E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.924 | TFLOPs: 8.41 | +31: iteration 11150/ 37905 | consumed samples: 2854400 | consumed tokens: 5845811200 | elapsed time per iteration (s): 0.21 | learning rate: 1.642E-04 | global batch size: 256 | lm loss: 3.028374E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.600 | TFLOPs: 7.72 | +31: iteration 11160/ 37905 | consumed samples: 2856960 | consumed tokens: 5851054080 | elapsed time per iteration (s): 0.19 | learning rate: 1.642E-04 | global batch size: 256 | lm loss: 3.047546E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.523 | TFLOPs: 8.37 | +31: iteration 11170/ 37905 | consumed samples: 2859520 | consumed tokens: 5856296960 | elapsed time per iteration (s): 0.21 | learning rate: 1.641E-04 | global batch size: 256 | lm loss: 3.041156E+00 | grad norm: 0.305 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.641 | TFLOPs: 7.77 | +31: iteration 11180/ 37905 | consumed samples: 2862080 | consumed tokens: 5861539840 | elapsed time per iteration (s): 0.21 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 3.045612E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.161 | TFLOPs: 7.91 | +31: iteration 11190/ 37905 | consumed samples: 2864640 | consumed tokens: 5866782720 | elapsed time per iteration (s): 0.21 | learning rate: 1.640E-04 | global batch size: 256 | lm loss: 2.987352E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1214.506 | TFLOPs: 7.73 | +31: iteration 11200/ 37905 | consumed samples: 2867200 | consumed tokens: 5872025600 | elapsed time per iteration (s): 0.18 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 3.090403E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1409.238 | TFLOPs: 8.98 | +31: iteration 11210/ 37905 | consumed samples: 2869760 | consumed tokens: 5877268480 | elapsed time per iteration (s): 0.18 | learning rate: 1.639E-04 | global batch size: 256 | lm loss: 3.044868E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1404.745 | TFLOPs: 8.95 | +31: iteration 11220/ 37905 | consumed samples: 2872320 | consumed tokens: 5882511360 | elapsed time per iteration (s): 0.19 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 3.067936E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.585 | TFLOPs: 8.69 | +31: iteration 11230/ 37905 | consumed samples: 2874880 | consumed tokens: 5887754240 | elapsed time per iteration (s): 0.19 | learning rate: 1.638E-04 | global batch size: 256 | lm loss: 3.054571E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.244 | TFLOPs: 8.46 | +31: iteration 11240/ 37905 | consumed samples: 2877440 | consumed tokens: 5892997120 | elapsed time per iteration (s): 0.19 | learning rate: 1.637E-04 | global batch size: 256 | lm loss: 3.064171E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1359.973 | TFLOPs: 8.66 | +31: iteration 11250/ 37905 | consumed samples: 2880000 | consumed tokens: 5898240000 | elapsed time per iteration (s): 0.20 | learning rate: 1.636E-04 | global batch size: 256 | lm loss: 3.053543E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.925 | TFLOPs: 8.16 | +31: iteration 11260/ 37905 | consumed samples: 2882560 | consumed tokens: 5903482880 | elapsed time per iteration (s): 0.19 | learning rate: 1.636E-04 | global batch size: 256 | lm loss: 3.036028E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1360.612 | TFLOPs: 8.67 | +31: iteration 11270/ 37905 | consumed samples: 2885120 | consumed tokens: 5908725760 | elapsed time per iteration (s): 0.20 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 3.045393E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.643 | TFLOPs: 8.21 | +31: iteration 11280/ 37905 | consumed samples: 2887680 | consumed tokens: 5913968640 | elapsed time per iteration (s): 0.18 | learning rate: 1.635E-04 | global batch size: 256 | lm loss: 3.077294E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1409.333 | TFLOPs: 8.98 | +31: iteration 11290/ 37905 | consumed samples: 2890240 | consumed tokens: 5919211520 | elapsed time per iteration (s): 0.21 | learning rate: 1.634E-04 | global batch size: 256 | lm loss: 3.028201E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.889 | TFLOPs: 7.82 | +31: iteration 11300/ 37905 | consumed samples: 2892800 | consumed tokens: 5924454400 | elapsed time per iteration (s): 0.21 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 3.013108E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.570 | TFLOPs: 7.81 | +31: iteration 11310/ 37905 | consumed samples: 2895360 | consumed tokens: 5929697280 | elapsed time per iteration (s): 0.21 | learning rate: 1.633E-04 | global batch size: 256 | lm loss: 3.023300E+00 | grad norm: 0.346 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.020 | TFLOPs: 7.92 | +31: iteration 11320/ 37905 | consumed samples: 2897920 | consumed tokens: 5934940160 | elapsed time per iteration (s): 0.18 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 3.021790E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1410.866 | TFLOPs: 8.99 | +31: iteration 11330/ 37905 | consumed samples: 2900480 | consumed tokens: 5940183040 | elapsed time per iteration (s): 0.18 | learning rate: 1.632E-04 | global batch size: 256 | lm loss: 3.014734E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.835 | TFLOPs: 8.95 | +31: iteration 11340/ 37905 | consumed samples: 2903040 | consumed tokens: 5945425920 | elapsed time per iteration (s): 0.18 | learning rate: 1.631E-04 | global batch size: 256 | lm loss: 3.042410E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.195 | TFLOPs: 8.97 | +31: iteration 11350/ 37905 | consumed samples: 2905600 | consumed tokens: 5950668800 | elapsed time per iteration (s): 0.21 | learning rate: 1.630E-04 | global batch size: 256 | lm loss: 3.047443E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.681 | TFLOPs: 7.70 | +31: iteration 11360/ 37905 | consumed samples: 2908160 | consumed tokens: 5955911680 | elapsed time per iteration (s): 0.20 | learning rate: 1.630E-04 | global batch size: 256 | lm loss: 3.067143E+00 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.676 | TFLOPs: 8.18 | +31: iteration 11370/ 37905 | consumed samples: 2910720 | consumed tokens: 5961154560 | elapsed time per iteration (s): 0.20 | learning rate: 1.629E-04 | global batch size: 256 | lm loss: 3.039264E+00 | grad norm: 0.383 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.345 | TFLOPs: 8.31 | +31: iteration 11380/ 37905 | consumed samples: 2913280 | consumed tokens: 5966397440 | elapsed time per iteration (s): 0.20 | learning rate: 1.628E-04 | global batch size: 256 | lm loss: 3.035941E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.334 | TFLOPs: 8.10 | +31: iteration 11390/ 37905 | consumed samples: 2915840 | consumed tokens: 5971640320 | elapsed time per iteration (s): 0.20 | learning rate: 1.628E-04 | global batch size: 256 | lm loss: 3.024003E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.312 | TFLOPs: 8.08 | +31: iteration 11400/ 37905 | consumed samples: 2918400 | consumed tokens: 5976883200 | elapsed time per iteration (s): 0.18 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 3.070455E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.120 | TFLOPs: 8.95 | +31: iteration 11410/ 37905 | consumed samples: 2920960 | consumed tokens: 5982126080 | elapsed time per iteration (s): 0.17 | learning rate: 1.627E-04 | global batch size: 256 | lm loss: 3.002939E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1471.402 | TFLOPs: 9.37 | +31: iteration 11420/ 37905 | consumed samples: 2923520 | consumed tokens: 5987368960 | elapsed time per iteration (s): 0.20 | learning rate: 1.626E-04 | global batch size: 256 | lm loss: 3.005905E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1308.333 | TFLOPs: 8.33 | +31: iteration 11430/ 37905 | consumed samples: 2926080 | consumed tokens: 5992611840 | elapsed time per iteration (s): 0.17 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 3.021942E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1473.589 | TFLOPs: 9.38 | +31: iteration 11440/ 37905 | consumed samples: 2928640 | consumed tokens: 5997854720 | elapsed time per iteration (s): 0.18 | learning rate: 1.625E-04 | global batch size: 256 | lm loss: 3.053032E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.479 | TFLOPs: 8.93 | +31: iteration 11450/ 37905 | consumed samples: 2931200 | consumed tokens: 6003097600 | elapsed time per iteration (s): 0.20 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 3.011799E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.986 | TFLOPs: 8.18 | +31: iteration 11460/ 37905 | consumed samples: 2933760 | consumed tokens: 6008340480 | elapsed time per iteration (s): 0.18 | learning rate: 1.624E-04 | global batch size: 256 | lm loss: 3.032377E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1384.957 | TFLOPs: 8.82 | +31: iteration 11470/ 37905 | consumed samples: 2936320 | consumed tokens: 6013583360 | elapsed time per iteration (s): 0.19 | learning rate: 1.623E-04 | global batch size: 256 | lm loss: 3.058987E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.701 | TFLOPs: 8.55 | +31: iteration 11480/ 37905 | consumed samples: 2938880 | consumed tokens: 6018826240 | elapsed time per iteration (s): 0.20 | learning rate: 1.622E-04 | global batch size: 256 | lm loss: 3.061788E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.848 | TFLOPs: 8.06 | +31: iteration 11490/ 37905 | consumed samples: 2941440 | consumed tokens: 6024069120 | elapsed time per iteration (s): 0.21 | learning rate: 1.622E-04 | global batch size: 256 | lm loss: 3.050359E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.901 | TFLOPs: 7.62 | +31: iteration 11500/ 37905 | consumed samples: 2944000 | consumed tokens: 6029312000 | elapsed time per iteration (s): 0.20 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.064968E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.719 | TFLOPs: 8.15 | +31: iteration 11510/ 37905 | consumed samples: 2946560 | consumed tokens: 6034554880 | elapsed time per iteration (s): 0.20 | learning rate: 1.621E-04 | global batch size: 256 | lm loss: 3.058914E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.537 | TFLOPs: 8.31 | +31: iteration 11520/ 37905 | consumed samples: 2949120 | consumed tokens: 6039797760 | elapsed time per iteration (s): 0.17 | learning rate: 1.620E-04 | global batch size: 256 | lm loss: 3.032163E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1479.451 | TFLOPs: 9.42 | +31: iteration 11530/ 37905 | consumed samples: 2951680 | consumed tokens: 6045040640 | elapsed time per iteration (s): 0.19 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 3.002517E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1339.024 | TFLOPs: 8.53 | +31: iteration 11540/ 37905 | consumed samples: 2954240 | consumed tokens: 6050283520 | elapsed time per iteration (s): 0.21 | learning rate: 1.619E-04 | global batch size: 256 | lm loss: 3.055081E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.687 | TFLOPs: 7.60 | +31: iteration 11550/ 37905 | consumed samples: 2956800 | consumed tokens: 6055526400 | elapsed time per iteration (s): 0.18 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 3.055181E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1404.433 | TFLOPs: 8.94 | +31: iteration 11560/ 37905 | consumed samples: 2959360 | consumed tokens: 6060769280 | elapsed time per iteration (s): 0.19 | learning rate: 1.618E-04 | global batch size: 256 | lm loss: 3.046220E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.372 | TFLOPs: 8.54 | +31: iteration 11570/ 37905 | consumed samples: 2961920 | consumed tokens: 6066012160 | elapsed time per iteration (s): 0.20 | learning rate: 1.617E-04 | global batch size: 256 | lm loss: 3.024484E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.998 | TFLOPs: 8.18 | +31: iteration 11580/ 37905 | consumed samples: 2964480 | consumed tokens: 6071255040 | elapsed time per iteration (s): 0.19 | learning rate: 1.616E-04 | global batch size: 256 | lm loss: 3.004756E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.985 | TFLOPs: 8.54 | +31: iteration 11590/ 37905 | consumed samples: 2967040 | consumed tokens: 6076497920 | elapsed time per iteration (s): 0.18 | learning rate: 1.616E-04 | global batch size: 256 | lm loss: 3.042483E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1407.637 | TFLOPs: 8.96 | +31: iteration 11600/ 37905 | consumed samples: 2969600 | consumed tokens: 6081740800 | elapsed time per iteration (s): 0.21 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 3.046140E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.305 | TFLOPs: 7.59 | +31: iteration 11610/ 37905 | consumed samples: 2972160 | consumed tokens: 6086983680 | elapsed time per iteration (s): 0.24 | learning rate: 1.615E-04 | global batch size: 256 | lm loss: 3.049901E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.026 | TFLOPs: 6.87 | +31: iteration 11620/ 37905 | consumed samples: 2974720 | consumed tokens: 6092226560 | elapsed time per iteration (s): 0.20 | learning rate: 1.614E-04 | global batch size: 256 | lm loss: 3.073997E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.889 | TFLOPs: 8.22 | +31: iteration 11630/ 37905 | consumed samples: 2977280 | consumed tokens: 6097469440 | elapsed time per iteration (s): 0.19 | learning rate: 1.613E-04 | global batch size: 256 | lm loss: 3.020448E+00 | grad norm: 0.376 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.936 | TFLOPs: 8.69 | +31: iteration 11640/ 37905 | consumed samples: 2979840 | consumed tokens: 6102712320 | elapsed time per iteration (s): 0.20 | learning rate: 1.613E-04 | global batch size: 256 | lm loss: 3.059976E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1308.672 | TFLOPs: 8.33 | +31: iteration 11650/ 37905 | consumed samples: 2982400 | consumed tokens: 6107955200 | elapsed time per iteration (s): 0.19 | learning rate: 1.612E-04 | global batch size: 256 | lm loss: 3.003421E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.204 | TFLOPs: 8.39 | +31: iteration 11660/ 37905 | consumed samples: 2984960 | consumed tokens: 6113198080 | elapsed time per iteration (s): 0.22 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 3.038396E+00 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.792 | TFLOPs: 7.41 | +31: iteration 11670/ 37905 | consumed samples: 2987520 | consumed tokens: 6118440960 | elapsed time per iteration (s): 0.19 | learning rate: 1.611E-04 | global batch size: 256 | lm loss: 3.017473E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.698 | TFLOPs: 8.54 | +31: iteration 11680/ 37905 | consumed samples: 2990080 | consumed tokens: 6123683840 | elapsed time per iteration (s): 0.19 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 3.061200E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.939 | TFLOPs: 8.55 | +31: iteration 11690/ 37905 | consumed samples: 2992640 | consumed tokens: 6128926720 | elapsed time per iteration (s): 0.20 | learning rate: 1.610E-04 | global batch size: 256 | lm loss: 3.056227E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.805 | TFLOPs: 8.16 | +31: iteration 11700/ 37905 | consumed samples: 2995200 | consumed tokens: 6134169600 | elapsed time per iteration (s): 0.19 | learning rate: 1.609E-04 | global batch size: 256 | lm loss: 3.012874E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.947 | TFLOPs: 8.38 | +31: iteration 11710/ 37905 | consumed samples: 2997760 | consumed tokens: 6139412480 | elapsed time per iteration (s): 0.19 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 3.036734E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.021 | TFLOPs: 8.76 | +31: iteration 11720/ 37905 | consumed samples: 3000320 | consumed tokens: 6144655360 | elapsed time per iteration (s): 0.19 | learning rate: 1.608E-04 | global batch size: 256 | lm loss: 3.025949E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1336.480 | TFLOPs: 8.51 | +31: iteration 11730/ 37905 | consumed samples: 3002880 | consumed tokens: 6149898240 | elapsed time per iteration (s): 0.18 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 3.022076E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1407.947 | TFLOPs: 8.97 | +31: iteration 11740/ 37905 | consumed samples: 3005440 | consumed tokens: 6155141120 | elapsed time per iteration (s): 0.19 | learning rate: 1.607E-04 | global batch size: 256 | lm loss: 3.037138E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.015 | TFLOPs: 8.54 | +31: iteration 11750/ 37905 | consumed samples: 3008000 | consumed tokens: 6160384000 | elapsed time per iteration (s): 0.22 | learning rate: 1.606E-04 | global batch size: 256 | lm loss: 3.002090E+00 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.399 | TFLOPs: 7.40 | +31: iteration 11760/ 37905 | consumed samples: 3010560 | consumed tokens: 6165626880 | elapsed time per iteration (s): 0.18 | learning rate: 1.605E-04 | global batch size: 256 | lm loss: 3.042961E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1392.529 | TFLOPs: 8.87 | +31: iteration 11770/ 37905 | consumed samples: 3013120 | consumed tokens: 6170869760 | elapsed time per iteration (s): 0.18 | learning rate: 1.605E-04 | global batch size: 256 | lm loss: 3.052948E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1390.209 | TFLOPs: 8.85 | +31: iteration 11780/ 37905 | consumed samples: 3015680 | consumed tokens: 6176112640 | elapsed time per iteration (s): 0.19 | learning rate: 1.604E-04 | global batch size: 256 | lm loss: 3.013536E+00 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1366.287 | TFLOPs: 8.70 | +31: iteration 11790/ 37905 | consumed samples: 3018240 | consumed tokens: 6181355520 | elapsed time per iteration (s): 0.20 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 3.025824E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1302.929 | TFLOPs: 8.30 | +31: iteration 11800/ 37905 | consumed samples: 3020800 | consumed tokens: 6186598400 | elapsed time per iteration (s): 0.21 | learning rate: 1.603E-04 | global batch size: 256 | lm loss: 3.030167E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.421 | TFLOPs: 7.93 | +31: iteration 11810/ 37905 | consumed samples: 3023360 | consumed tokens: 6191841280 | elapsed time per iteration (s): 0.19 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 3.013826E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.048 | TFLOPs: 8.55 | +31: iteration 11820/ 37905 | consumed samples: 3025920 | consumed tokens: 6197084160 | elapsed time per iteration (s): 0.18 | learning rate: 1.602E-04 | global batch size: 256 | lm loss: 3.031062E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1409.601 | TFLOPs: 8.98 | +31: iteration 11830/ 37905 | consumed samples: 3028480 | consumed tokens: 6202327040 | elapsed time per iteration (s): 0.21 | learning rate: 1.601E-04 | global batch size: 256 | lm loss: 2.966528E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.474 | TFLOPs: 7.69 | +31: iteration 11840/ 37905 | consumed samples: 3031040 | consumed tokens: 6207569920 | elapsed time per iteration (s): 0.18 | learning rate: 1.600E-04 | global batch size: 256 | lm loss: 3.015942E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1436.195 | TFLOPs: 9.15 | +31: iteration 11850/ 37905 | consumed samples: 3033600 | consumed tokens: 6212812800 | elapsed time per iteration (s): 0.18 | learning rate: 1.600E-04 | global batch size: 256 | lm loss: 3.049221E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1392.555 | TFLOPs: 8.87 | +31: iteration 11860/ 37905 | consumed samples: 3036160 | consumed tokens: 6218055680 | elapsed time per iteration (s): 0.19 | learning rate: 1.599E-04 | global batch size: 256 | lm loss: 2.974720E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1379.363 | TFLOPs: 8.78 | +31: iteration 11870/ 37905 | consumed samples: 3038720 | consumed tokens: 6223298560 | elapsed time per iteration (s): 0.18 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 3.030687E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.131 | TFLOPs: 8.97 | +31: iteration 11880/ 37905 | consumed samples: 3041280 | consumed tokens: 6228541440 | elapsed time per iteration (s): 0.20 | learning rate: 1.598E-04 | global batch size: 256 | lm loss: 3.023614E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1259.724 | TFLOPs: 8.02 | +31: iteration 11890/ 37905 | consumed samples: 3043840 | consumed tokens: 6233784320 | elapsed time per iteration (s): 0.18 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 3.046077E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1406.619 | TFLOPs: 8.96 | +31: iteration 11900/ 37905 | consumed samples: 3046400 | consumed tokens: 6239027200 | elapsed time per iteration (s): 0.20 | learning rate: 1.597E-04 | global batch size: 256 | lm loss: 2.997468E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.172 | TFLOPs: 8.36 | +31: iteration 11910/ 37905 | consumed samples: 3048960 | consumed tokens: 6244270080 | elapsed time per iteration (s): 0.19 | learning rate: 1.596E-04 | global batch size: 256 | lm loss: 3.060177E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.821 | TFLOPs: 8.36 | +31: iteration 11920/ 37905 | consumed samples: 3051520 | consumed tokens: 6249512960 | elapsed time per iteration (s): 0.18 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 3.058544E+00 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1409.854 | TFLOPs: 8.98 | +31: iteration 11930/ 37905 | consumed samples: 3054080 | consumed tokens: 6254755840 | elapsed time per iteration (s): 0.19 | learning rate: 1.595E-04 | global batch size: 256 | lm loss: 3.051449E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1374.831 | TFLOPs: 8.76 | +31: iteration 11940/ 37905 | consumed samples: 3056640 | consumed tokens: 6259998720 | elapsed time per iteration (s): 0.20 | learning rate: 1.594E-04 | global batch size: 256 | lm loss: 3.051130E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.181 | TFLOPs: 8.17 | +31: iteration 11950/ 37905 | consumed samples: 3059200 | consumed tokens: 6265241600 | elapsed time per iteration (s): 0.18 | learning rate: 1.594E-04 | global batch size: 256 | lm loss: 2.988541E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1407.346 | TFLOPs: 8.96 | +31: iteration 11960/ 37905 | consumed samples: 3061760 | consumed tokens: 6270484480 | elapsed time per iteration (s): 0.21 | learning rate: 1.593E-04 | global batch size: 256 | lm loss: 3.028842E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.629 | TFLOPs: 7.63 | +31: iteration 11970/ 37905 | consumed samples: 3064320 | consumed tokens: 6275727360 | elapsed time per iteration (s): 0.19 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 3.023227E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1336.596 | TFLOPs: 8.51 | +31: iteration 11980/ 37905 | consumed samples: 3066880 | consumed tokens: 6280970240 | elapsed time per iteration (s): 0.19 | learning rate: 1.592E-04 | global batch size: 256 | lm loss: 3.057132E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1369.013 | TFLOPs: 8.72 | +31: iteration 11990/ 37905 | consumed samples: 3069440 | consumed tokens: 6286213120 | elapsed time per iteration (s): 0.19 | learning rate: 1.591E-04 | global batch size: 256 | lm loss: 3.024464E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.918 | TFLOPs: 8.46 | + 0: [2022-11-24 14:53:54,190] [INFO] [logging.py:68:log_dist] [Rank 0] step=12000, skipped=0, lr=[0.00015903800536307795, 0.00015903800536307795, 0.00015903800536307795], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 12000/ 37905 | consumed samples: 3072000 | consumed tokens: 6291456000 | elapsed time per iteration (s): 0.21 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 3.057436E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.478 | TFLOPs: 7.94 | + 0: steps: 12000 loss: 3.1192 iter time (s): 0.193 samples/sec: 1323.655 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 12000 | lm loss value: 2.977173E+00 | lm loss PPL: 1.963223E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 12000 to checkpoints_83m + 0: [2022-11-24 14:53:54,311] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step12000 is begin to save! + 0: [2022-11-24 14:53:54,320] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,392] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,404] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,436] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,447] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,469] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,502] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:53:54,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:53:54,504] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step12000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:53:54,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:53:54,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,570] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step12000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:53:54,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:53:54,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +13: [2022-11-24 14:53:54,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +12: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:53:54,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 8: [2022-11-24 14:53:54,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:53:54,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:53:54,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +30: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +13: [2022-11-24 14:53:54,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:53:54,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:53:54,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:53:54,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:53:54,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +17: [2022-11-24 14:53:54,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +12: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +10: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +11: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 8: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +10: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +19: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +19: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:53:54,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:53:54,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +28: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:53:54,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +18: [2022-11-24 14:53:54,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +30: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:53:54,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +15: [2022-11-24 14:53:54,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 14:53:54,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:53:54,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:53:54,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:53:54,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:53:54,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +12: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:53:54,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 6: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 6: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 8: [2022-11-24 14:53:54,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:53:54,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +28: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +26: [2022-11-24 14:53:54,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:53:54,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 14:53:54,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:53:54,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +22: [2022-11-24 14:53:54,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:53:54,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +30: [2022-11-24 14:53:54,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +13: [2022-11-24 14:53:54,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:53:54,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +17: [2022-11-24 14:53:54,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:53:54,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:53:54,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +19: [2022-11-24 14:53:54,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:53:54,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:53:54,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +10: [2022-11-24 14:53:54,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +12: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 8: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:53:54,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:53:54,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 6: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +28: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +26: [2022-11-24 14:53:54,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 14:53:54,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:53:54,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:53:54,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +18: [2022-11-24 14:53:54,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:53:54,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +30: [2022-11-24 14:53:54,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +15: [2022-11-24 14:53:54,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:53:54,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +29: [2022-11-24 14:53:54,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +13: [2022-11-24 14:53:54,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +17: [2022-11-24 14:53:54,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:53:54,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:53:54,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:53:54,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +10: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +12: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:53:54,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:53:54,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:53:54,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 6: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:53:54,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +26: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:53:54,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +22: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:53:54,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +30: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +18: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +30: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +15: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 14:53:54,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:53:54,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +17: [2022-11-24 14:53:54,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:53:54,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:53:54,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:53:54,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 14:53:54,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 14:53:54,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +12: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 8: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:53:54,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:53:54,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +28: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 6: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +26: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:53:54,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:53:54,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +22: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:53:54,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +18: [2022-11-24 14:53:54,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +30: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +15: [2022-11-24 14:53:54,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:53:54,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +13: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +17: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:53:54,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:53:54,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +19: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +12: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 8: [2022-11-24 14:53:54,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +28: [2022-11-24 14:53:54,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +26: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:53:54,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +22: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +30: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +31: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +15: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +18: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +28: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +19: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +28: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +27: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 2: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +26: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +15: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +17: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +27: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 8: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +26: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +15: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 9: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +28: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +25: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +22: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 4: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +24: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +25: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +10: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +14: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +26: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +24: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +18: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +17: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +11: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +12: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +10: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +22: [2022-11-24 14:53:54,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +20: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +26: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +17: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +10: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +14: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 6: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +21: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +11: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +29: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 5: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 1: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 6: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +21: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +16: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +16: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 3: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 7: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! +23: [2022-11-24 14:53:54,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step12000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 14:53:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step12000 is ready now! + 0: successfully saved checkpoint at iteration 12000 to checkpoints_83m +31: time (ms) | save-checkpoint: 316.87 +31: iteration 12010/ 37905 | consumed samples: 3074560 | consumed tokens: 6296698880 | elapsed time per iteration (s): 0.23 | learning rate: 1.590E-04 | global batch size: 256 | lm loss: 3.021272E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.700 | TFLOPs: 6.98 | +31: iteration 12020/ 37905 | consumed samples: 3077120 | consumed tokens: 6301941760 | elapsed time per iteration (s): 0.19 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 2.983082E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.513 | TFLOPs: 8.78 | +31: iteration 12030/ 37905 | consumed samples: 3079680 | consumed tokens: 6307184640 | elapsed time per iteration (s): 0.19 | learning rate: 1.589E-04 | global batch size: 256 | lm loss: 3.000539E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.228 | TFLOPs: 8.46 | +31: iteration 12040/ 37905 | consumed samples: 3082240 | consumed tokens: 6312427520 | elapsed time per iteration (s): 0.20 | learning rate: 1.588E-04 | global batch size: 256 | lm loss: 3.020601E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.614 | TFLOPs: 8.36 | +31: iteration 12050/ 37905 | consumed samples: 3084800 | consumed tokens: 6317670400 | elapsed time per iteration (s): 0.22 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 2.998766E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.328 | TFLOPs: 7.40 | +31: iteration 12060/ 37905 | consumed samples: 3087360 | consumed tokens: 6322913280 | elapsed time per iteration (s): 0.19 | learning rate: 1.587E-04 | global batch size: 256 | lm loss: 3.008258E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1356.830 | TFLOPs: 8.64 | +31: iteration 12070/ 37905 | consumed samples: 3089920 | consumed tokens: 6328156160 | elapsed time per iteration (s): 0.19 | learning rate: 1.586E-04 | global batch size: 256 | lm loss: 3.032217E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.419 | TFLOPs: 8.38 | +31: iteration 12080/ 37905 | consumed samples: 3092480 | consumed tokens: 6333399040 | elapsed time per iteration (s): 0.20 | learning rate: 1.585E-04 | global batch size: 256 | lm loss: 3.012837E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.865 | TFLOPs: 8.14 | +31: iteration 12090/ 37905 | consumed samples: 3095040 | consumed tokens: 6338641920 | elapsed time per iteration (s): 0.19 | learning rate: 1.585E-04 | global batch size: 256 | lm loss: 3.010147E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.627 | TFLOPs: 8.58 | +31: iteration 12100/ 37905 | consumed samples: 3097600 | consumed tokens: 6343884800 | elapsed time per iteration (s): 0.18 | learning rate: 1.584E-04 | global batch size: 256 | lm loss: 3.004557E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1406.803 | TFLOPs: 8.96 | +31: iteration 12110/ 37905 | consumed samples: 3100160 | consumed tokens: 6349127680 | elapsed time per iteration (s): 0.19 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 2.978004E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.438 | TFLOPs: 8.56 | +31: iteration 12120/ 37905 | consumed samples: 3102720 | consumed tokens: 6354370560 | elapsed time per iteration (s): 0.20 | learning rate: 1.583E-04 | global batch size: 256 | lm loss: 3.036142E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.400 | TFLOPs: 8.15 | +31: iteration 12130/ 37905 | consumed samples: 3105280 | consumed tokens: 6359613440 | elapsed time per iteration (s): 0.19 | learning rate: 1.582E-04 | global batch size: 256 | lm loss: 3.044280E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.605 | TFLOPs: 8.54 | +31: iteration 12140/ 37905 | consumed samples: 3107840 | consumed tokens: 6364856320 | elapsed time per iteration (s): 0.17 | learning rate: 1.582E-04 | global batch size: 256 | lm loss: 3.039518E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1469.676 | TFLOPs: 9.36 | +31: iteration 12150/ 37905 | consumed samples: 3110400 | consumed tokens: 6370099200 | elapsed time per iteration (s): 0.19 | learning rate: 1.581E-04 | global batch size: 256 | lm loss: 3.046191E+00 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.633 | TFLOPs: 8.69 | +31: iteration 12160/ 37905 | consumed samples: 3112960 | consumed tokens: 6375342080 | elapsed time per iteration (s): 0.18 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 3.005585E+00 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1425.815 | TFLOPs: 9.08 | +31: iteration 12170/ 37905 | consumed samples: 3115520 | consumed tokens: 6380584960 | elapsed time per iteration (s): 0.18 | learning rate: 1.580E-04 | global batch size: 256 | lm loss: 2.965158E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1436.643 | TFLOPs: 9.15 | +31: iteration 12180/ 37905 | consumed samples: 3118080 | consumed tokens: 6385827840 | elapsed time per iteration (s): 0.18 | learning rate: 1.579E-04 | global batch size: 256 | lm loss: 3.005066E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.762 | TFLOPs: 8.93 | +31: iteration 12190/ 37905 | consumed samples: 3120640 | consumed tokens: 6391070720 | elapsed time per iteration (s): 0.19 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 3.006350E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.432 | TFLOPs: 8.56 | +31: iteration 12200/ 37905 | consumed samples: 3123200 | consumed tokens: 6396313600 | elapsed time per iteration (s): 0.19 | learning rate: 1.578E-04 | global batch size: 256 | lm loss: 3.047812E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.447 | TFLOPs: 8.45 | +31: iteration 12210/ 37905 | consumed samples: 3125760 | consumed tokens: 6401556480 | elapsed time per iteration (s): 0.19 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 3.039762E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1322.862 | TFLOPs: 8.43 | +31: iteration 12220/ 37905 | consumed samples: 3128320 | consumed tokens: 6406799360 | elapsed time per iteration (s): 0.19 | learning rate: 1.577E-04 | global batch size: 256 | lm loss: 3.029270E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1351.291 | TFLOPs: 8.61 | +31: iteration 12230/ 37905 | consumed samples: 3130880 | consumed tokens: 6412042240 | elapsed time per iteration (s): 0.18 | learning rate: 1.576E-04 | global batch size: 256 | lm loss: 3.022459E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1437.160 | TFLOPs: 9.15 | +31: iteration 12240/ 37905 | consumed samples: 3133440 | consumed tokens: 6417285120 | elapsed time per iteration (s): 0.17 | learning rate: 1.575E-04 | global batch size: 256 | lm loss: 2.985743E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1472.453 | TFLOPs: 9.38 | +31: iteration 12250/ 37905 | consumed samples: 3136000 | consumed tokens: 6422528000 | elapsed time per iteration (s): 0.19 | learning rate: 1.575E-04 | global batch size: 256 | lm loss: 3.026024E+00 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.780 | TFLOPs: 8.54 | +31: iteration 12260/ 37905 | consumed samples: 3138560 | consumed tokens: 6427770880 | elapsed time per iteration (s): 0.17 | learning rate: 1.574E-04 | global batch size: 256 | lm loss: 3.030468E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1471.055 | TFLOPs: 9.37 | +31: iteration 12270/ 37905 | consumed samples: 3141120 | consumed tokens: 6433013760 | elapsed time per iteration (s): 0.19 | learning rate: 1.573E-04 | global batch size: 256 | lm loss: 3.023532E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.532 | TFLOPs: 8.76 | +31: iteration 12280/ 37905 | consumed samples: 3143680 | consumed tokens: 6438256640 | elapsed time per iteration (s): 0.19 | learning rate: 1.573E-04 | global batch size: 256 | lm loss: 3.024579E+00 | grad norm: 0.301 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.287 | TFLOPs: 8.43 | +31: iteration 12290/ 37905 | consumed samples: 3146240 | consumed tokens: 6443499520 | elapsed time per iteration (s): 0.20 | learning rate: 1.572E-04 | global batch size: 256 | lm loss: 3.035131E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.004 | TFLOPs: 8.18 | +31: iteration 12300/ 37905 | consumed samples: 3148800 | consumed tokens: 6448742400 | elapsed time per iteration (s): 0.19 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 3.018573E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1378.305 | TFLOPs: 8.78 | +31: iteration 12310/ 37905 | consumed samples: 3151360 | consumed tokens: 6453985280 | elapsed time per iteration (s): 0.19 | learning rate: 1.571E-04 | global batch size: 256 | lm loss: 3.041629E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1339.422 | TFLOPs: 8.53 | +31: iteration 12320/ 37905 | consumed samples: 3153920 | consumed tokens: 6459228160 | elapsed time per iteration (s): 0.20 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 3.009656E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.913 | TFLOPs: 8.14 | +31: iteration 12330/ 37905 | consumed samples: 3156480 | consumed tokens: 6464471040 | elapsed time per iteration (s): 0.22 | learning rate: 1.570E-04 | global batch size: 256 | lm loss: 3.052549E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.514 | TFLOPs: 7.37 | +31: iteration 12340/ 37905 | consumed samples: 3159040 | consumed tokens: 6469713920 | elapsed time per iteration (s): 0.17 | learning rate: 1.569E-04 | global batch size: 256 | lm loss: 3.039647E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1474.480 | TFLOPs: 9.39 | +31: iteration 12350/ 37905 | consumed samples: 3161600 | consumed tokens: 6474956800 | elapsed time per iteration (s): 0.19 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 3.018902E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.427 | TFLOPs: 8.54 | +31: iteration 12360/ 37905 | consumed samples: 3164160 | consumed tokens: 6480199680 | elapsed time per iteration (s): 0.18 | learning rate: 1.568E-04 | global batch size: 256 | lm loss: 3.026348E+00 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.819 | TFLOPs: 8.95 | +31: iteration 12370/ 37905 | consumed samples: 3166720 | consumed tokens: 6485442560 | elapsed time per iteration (s): 0.19 | learning rate: 1.567E-04 | global batch size: 256 | lm loss: 3.016435E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1376.081 | TFLOPs: 8.76 | +31: iteration 12380/ 37905 | consumed samples: 3169280 | consumed tokens: 6490685440 | elapsed time per iteration (s): 0.20 | learning rate: 1.566E-04 | global batch size: 256 | lm loss: 3.030538E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.727 | TFLOPs: 8.07 | +31: iteration 12390/ 37905 | consumed samples: 3171840 | consumed tokens: 6495928320 | elapsed time per iteration (s): 0.17 | learning rate: 1.566E-04 | global batch size: 256 | lm loss: 2.989692E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1477.833 | TFLOPs: 9.41 | +31: iteration 12400/ 37905 | consumed samples: 3174400 | consumed tokens: 6501171200 | elapsed time per iteration (s): 0.18 | learning rate: 1.565E-04 | global batch size: 256 | lm loss: 3.052009E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1405.992 | TFLOPs: 8.95 | +31: iteration 12410/ 37905 | consumed samples: 3176960 | consumed tokens: 6506414080 | elapsed time per iteration (s): 0.18 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 3.054521E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1407.671 | TFLOPs: 8.97 | +31: iteration 12420/ 37905 | consumed samples: 3179520 | consumed tokens: 6511656960 | elapsed time per iteration (s): 0.23 | learning rate: 1.564E-04 | global batch size: 256 | lm loss: 3.017746E+00 | grad norm: 0.323 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.561 | TFLOPs: 7.03 | +31: iteration 12430/ 37905 | consumed samples: 3182080 | consumed tokens: 6516899840 | elapsed time per iteration (s): 0.18 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 3.026903E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.395 | TFLOPs: 8.93 | +31: iteration 12440/ 37905 | consumed samples: 3184640 | consumed tokens: 6522142720 | elapsed time per iteration (s): 0.20 | learning rate: 1.563E-04 | global batch size: 256 | lm loss: 3.001028E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.756 | TFLOPs: 8.36 | +31: iteration 12450/ 37905 | consumed samples: 3187200 | consumed tokens: 6527385600 | elapsed time per iteration (s): 0.20 | learning rate: 1.562E-04 | global batch size: 256 | lm loss: 3.026378E+00 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.939 | TFLOPs: 8.08 | +31: iteration 12460/ 37905 | consumed samples: 3189760 | consumed tokens: 6532628480 | elapsed time per iteration (s): 0.21 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 3.051998E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.615 | TFLOPs: 7.59 | +31: iteration 12470/ 37905 | consumed samples: 3192320 | consumed tokens: 6537871360 | elapsed time per iteration (s): 0.17 | learning rate: 1.561E-04 | global batch size: 256 | lm loss: 3.023108E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1468.342 | TFLOPs: 9.35 | +31: iteration 12480/ 37905 | consumed samples: 3194880 | consumed tokens: 6543114240 | elapsed time per iteration (s): 0.22 | learning rate: 1.560E-04 | global batch size: 256 | lm loss: 2.991282E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.111 | TFLOPs: 7.55 | +31: iteration 12490/ 37905 | consumed samples: 3197440 | consumed tokens: 6548357120 | elapsed time per iteration (s): 0.18 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 2.990541E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.689 | TFLOPs: 8.97 | +31: iteration 12500/ 37905 | consumed samples: 3200000 | consumed tokens: 6553600000 | elapsed time per iteration (s): 0.19 | learning rate: 1.559E-04 | global batch size: 256 | lm loss: 2.999514E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1351.215 | TFLOPs: 8.61 | +31: iteration 12510/ 37905 | consumed samples: 3202560 | consumed tokens: 6558842880 | elapsed time per iteration (s): 0.18 | learning rate: 1.558E-04 | global batch size: 256 | lm loss: 2.994269E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1403.415 | TFLOPs: 8.94 | +31: iteration 12520/ 37905 | consumed samples: 3205120 | consumed tokens: 6564085760 | elapsed time per iteration (s): 0.23 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 3.029862E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.357 | TFLOPs: 7.23 | +31: iteration 12530/ 37905 | consumed samples: 3207680 | consumed tokens: 6569328640 | elapsed time per iteration (s): 0.20 | learning rate: 1.557E-04 | global batch size: 256 | lm loss: 3.002274E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.456 | TFLOPs: 7.96 | +31: iteration 12540/ 37905 | consumed samples: 3210240 | consumed tokens: 6574571520 | elapsed time per iteration (s): 0.20 | learning rate: 1.556E-04 | global batch size: 256 | lm loss: 2.980290E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1259.235 | TFLOPs: 8.02 | +31: iteration 12550/ 37905 | consumed samples: 3212800 | consumed tokens: 6579814400 | elapsed time per iteration (s): 0.20 | learning rate: 1.555E-04 | global batch size: 256 | lm loss: 3.019255E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.500 | TFLOPs: 8.07 | +31: iteration 12560/ 37905 | consumed samples: 3215360 | consumed tokens: 6585057280 | elapsed time per iteration (s): 0.19 | learning rate: 1.555E-04 | global batch size: 256 | lm loss: 3.058256E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1377.126 | TFLOPs: 8.77 | +31: iteration 12570/ 37905 | consumed samples: 3217920 | consumed tokens: 6590300160 | elapsed time per iteration (s): 0.18 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 3.019123E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1386.985 | TFLOPs: 8.83 | +31: iteration 12580/ 37905 | consumed samples: 3220480 | consumed tokens: 6595543040 | elapsed time per iteration (s): 0.21 | learning rate: 1.554E-04 | global batch size: 256 | lm loss: 3.014866E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.306 | TFLOPs: 7.82 | +31: iteration 12590/ 37905 | consumed samples: 3223040 | consumed tokens: 6600785920 | elapsed time per iteration (s): 0.20 | learning rate: 1.553E-04 | global batch size: 256 | lm loss: 3.042765E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1297.897 | TFLOPs: 8.27 | +31: iteration 12600/ 37905 | consumed samples: 3225600 | consumed tokens: 6606028800 | elapsed time per iteration (s): 0.18 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 3.009470E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1458.608 | TFLOPs: 9.29 | +31: iteration 12610/ 37905 | consumed samples: 3228160 | consumed tokens: 6611271680 | elapsed time per iteration (s): 0.22 | learning rate: 1.552E-04 | global batch size: 256 | lm loss: 3.006007E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.344 | TFLOPs: 7.26 | +31: iteration 12620/ 37905 | consumed samples: 3230720 | consumed tokens: 6616514560 | elapsed time per iteration (s): 0.27 | learning rate: 1.551E-04 | global batch size: 256 | lm loss: 2.986675E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 959.714 | TFLOPs: 6.11 | +31: iteration 12630/ 37905 | consumed samples: 3233280 | consumed tokens: 6621757440 | elapsed time per iteration (s): 0.20 | learning rate: 1.550E-04 | global batch size: 256 | lm loss: 3.053707E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1259.203 | TFLOPs: 8.02 | +31: iteration 12640/ 37905 | consumed samples: 3235840 | consumed tokens: 6627000320 | elapsed time per iteration (s): 0.18 | learning rate: 1.550E-04 | global batch size: 256 | lm loss: 3.018841E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1384.424 | TFLOPs: 8.82 | +31: iteration 12650/ 37905 | consumed samples: 3238400 | consumed tokens: 6632243200 | elapsed time per iteration (s): 0.19 | learning rate: 1.549E-04 | global batch size: 256 | lm loss: 2.998026E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.359 | TFLOPs: 8.69 | +31: iteration 12660/ 37905 | consumed samples: 3240960 | consumed tokens: 6637486080 | elapsed time per iteration (s): 0.17 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 3.010727E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1482.452 | TFLOPs: 9.44 | +31: iteration 12670/ 37905 | consumed samples: 3243520 | consumed tokens: 6642728960 | elapsed time per iteration (s): 0.18 | learning rate: 1.548E-04 | global batch size: 256 | lm loss: 3.005190E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.397 | TFLOPs: 8.97 | +31: iteration 12680/ 37905 | consumed samples: 3246080 | consumed tokens: 6647971840 | elapsed time per iteration (s): 0.20 | learning rate: 1.547E-04 | global batch size: 256 | lm loss: 3.045850E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.445 | TFLOPs: 7.98 | +31: iteration 12690/ 37905 | consumed samples: 3248640 | consumed tokens: 6653214720 | elapsed time per iteration (s): 0.21 | learning rate: 1.546E-04 | global batch size: 256 | lm loss: 3.000099E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.242 | TFLOPs: 7.66 | +31: iteration 12700/ 37905 | consumed samples: 3251200 | consumed tokens: 6658457600 | elapsed time per iteration (s): 0.20 | learning rate: 1.546E-04 | global batch size: 256 | lm loss: 3.013260E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.827 | TFLOPs: 8.12 | +31: iteration 12710/ 37905 | consumed samples: 3253760 | consumed tokens: 6663700480 | elapsed time per iteration (s): 0.21 | learning rate: 1.545E-04 | global batch size: 256 | lm loss: 2.998675E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.231 | TFLOPs: 7.80 | +31: iteration 12720/ 37905 | consumed samples: 3256320 | consumed tokens: 6668943360 | elapsed time per iteration (s): 0.20 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 2.991446E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.979 | TFLOPs: 8.36 | +31: iteration 12730/ 37905 | consumed samples: 3258880 | consumed tokens: 6674186240 | elapsed time per iteration (s): 0.22 | learning rate: 1.544E-04 | global batch size: 256 | lm loss: 2.988744E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.547 | TFLOPs: 7.58 | +31: iteration 12740/ 37905 | consumed samples: 3261440 | consumed tokens: 6679429120 | elapsed time per iteration (s): 0.19 | learning rate: 1.543E-04 | global batch size: 256 | lm loss: 3.000824E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.673 | TFLOPs: 8.54 | +31: iteration 12750/ 37905 | consumed samples: 3264000 | consumed tokens: 6684672000 | elapsed time per iteration (s): 0.21 | learning rate: 1.543E-04 | global batch size: 256 | lm loss: 3.039594E+00 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.285 | TFLOPs: 7.71 | +31: iteration 12760/ 37905 | consumed samples: 3266560 | consumed tokens: 6689914880 | elapsed time per iteration (s): 0.19 | learning rate: 1.542E-04 | global batch size: 256 | lm loss: 3.008463E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1349.030 | TFLOPs: 8.59 | +31: iteration 12770/ 37905 | consumed samples: 3269120 | consumed tokens: 6695157760 | elapsed time per iteration (s): 0.19 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 2.998231E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.221 | TFLOPs: 8.44 | +31: iteration 12780/ 37905 | consumed samples: 3271680 | consumed tokens: 6700400640 | elapsed time per iteration (s): 0.19 | learning rate: 1.541E-04 | global batch size: 256 | lm loss: 3.014699E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.041 | TFLOPs: 8.39 | +31: iteration 12790/ 37905 | consumed samples: 3274240 | consumed tokens: 6705643520 | elapsed time per iteration (s): 0.18 | learning rate: 1.540E-04 | global batch size: 256 | lm loss: 3.002061E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1438.522 | TFLOPs: 9.16 | +31: iteration 12800/ 37905 | consumed samples: 3276800 | consumed tokens: 6710886400 | elapsed time per iteration (s): 0.20 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 3.028861E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1309.041 | TFLOPs: 8.34 | +31: iteration 12810/ 37905 | consumed samples: 3279360 | consumed tokens: 6716129280 | elapsed time per iteration (s): 0.17 | learning rate: 1.539E-04 | global batch size: 256 | lm loss: 3.009568E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1484.043 | TFLOPs: 9.45 | +31: iteration 12820/ 37905 | consumed samples: 3281920 | consumed tokens: 6721372160 | elapsed time per iteration (s): 0.20 | learning rate: 1.538E-04 | global batch size: 256 | lm loss: 3.004535E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.394 | TFLOPs: 8.21 | +31: iteration 12830/ 37905 | consumed samples: 3284480 | consumed tokens: 6726615040 | elapsed time per iteration (s): 0.18 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 3.011732E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.689 | TFLOPs: 8.97 | +31: iteration 12840/ 37905 | consumed samples: 3287040 | consumed tokens: 6731857920 | elapsed time per iteration (s): 0.21 | learning rate: 1.537E-04 | global batch size: 256 | lm loss: 3.003250E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.188 | TFLOPs: 7.89 | +31: iteration 12850/ 37905 | consumed samples: 3289600 | consumed tokens: 6737100800 | elapsed time per iteration (s): 0.20 | learning rate: 1.536E-04 | global batch size: 256 | lm loss: 2.960236E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.482 | TFLOPs: 8.03 | +31: iteration 12860/ 37905 | consumed samples: 3292160 | consumed tokens: 6742343680 | elapsed time per iteration (s): 0.19 | learning rate: 1.535E-04 | global batch size: 256 | lm loss: 2.997857E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1362.007 | TFLOPs: 8.67 | +31: iteration 12870/ 37905 | consumed samples: 3294720 | consumed tokens: 6747586560 | elapsed time per iteration (s): 0.17 | learning rate: 1.535E-04 | global batch size: 256 | lm loss: 2.991968E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1492.589 | TFLOPs: 9.51 | +31: iteration 12880/ 37905 | consumed samples: 3297280 | consumed tokens: 6752829440 | elapsed time per iteration (s): 0.21 | learning rate: 1.534E-04 | global batch size: 256 | lm loss: 3.026150E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.831 | TFLOPs: 7.73 | +31: iteration 12890/ 37905 | consumed samples: 3299840 | consumed tokens: 6758072320 | elapsed time per iteration (s): 0.21 | learning rate: 1.533E-04 | global batch size: 256 | lm loss: 3.023794E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.480 | TFLOPs: 7.70 | +31: iteration 12900/ 37905 | consumed samples: 3302400 | consumed tokens: 6763315200 | elapsed time per iteration (s): 0.22 | learning rate: 1.533E-04 | global batch size: 256 | lm loss: 3.019214E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.267 | TFLOPs: 7.56 | +31: iteration 12910/ 37905 | consumed samples: 3304960 | consumed tokens: 6768558080 | elapsed time per iteration (s): 0.19 | learning rate: 1.532E-04 | global batch size: 256 | lm loss: 3.008312E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1339.681 | TFLOPs: 8.53 | +31: iteration 12920/ 37905 | consumed samples: 3307520 | consumed tokens: 6773800960 | elapsed time per iteration (s): 0.20 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 3.053755E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1260.988 | TFLOPs: 8.03 | +31: iteration 12930/ 37905 | consumed samples: 3310080 | consumed tokens: 6779043840 | elapsed time per iteration (s): 0.19 | learning rate: 1.531E-04 | global batch size: 256 | lm loss: 3.022317E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.471 | TFLOPs: 8.40 | +31: iteration 12940/ 37905 | consumed samples: 3312640 | consumed tokens: 6784286720 | elapsed time per iteration (s): 0.18 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 3.024849E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1412.670 | TFLOPs: 9.00 | +31: iteration 12950/ 37905 | consumed samples: 3315200 | consumed tokens: 6789529600 | elapsed time per iteration (s): 0.19 | learning rate: 1.530E-04 | global batch size: 256 | lm loss: 2.999714E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1344.943 | TFLOPs: 8.57 | +31: iteration 12960/ 37905 | consumed samples: 3317760 | consumed tokens: 6794772480 | elapsed time per iteration (s): 0.18 | learning rate: 1.529E-04 | global batch size: 256 | lm loss: 2.974326E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1411.207 | TFLOPs: 8.99 | +31: iteration 12970/ 37905 | consumed samples: 3320320 | consumed tokens: 6800015360 | elapsed time per iteration (s): 0.21 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 2.993708E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.526 | TFLOPs: 7.82 | +31: iteration 12980/ 37905 | consumed samples: 3322880 | consumed tokens: 6805258240 | elapsed time per iteration (s): 0.19 | learning rate: 1.528E-04 | global batch size: 256 | lm loss: 3.024055E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1351.168 | TFLOPs: 8.61 | +31: iteration 12990/ 37905 | consumed samples: 3325440 | consumed tokens: 6810501120 | elapsed time per iteration (s): 0.19 | learning rate: 1.527E-04 | global batch size: 256 | lm loss: 2.971874E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.539 | TFLOPs: 8.54 | +31: iteration 13000/ 37905 | consumed samples: 3328000 | consumed tokens: 6815744000 | elapsed time per iteration (s): 0.20 | learning rate: 1.526E-04 | global batch size: 256 | lm loss: 3.019900E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1259.223 | TFLOPs: 8.02 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 13000 | lm loss value: 2.888258E+00 | lm loss PPL: 1.796199E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 13000 to checkpoints_83m + 0: [2022-11-24 14:57:08,914] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step13000 is begin to save! + 0: [2022-11-24 14:57:08,923] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 14:57:08,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 14:57:08,994] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,019] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,030] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,042] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,053] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,064] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,074] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,074] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,085] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,096] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,107] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 14:57:09,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 14:57:09,109] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step13000/mp_rank_00_model_states.pt + 0: [2022-11-24 14:57:09,109] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/mp_rank_00_model_states.pt... + 0: [2022-11-24 14:57:09,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/mp_rank_00_model_states.pt. + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +14: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +20: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... + 9: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +27: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +10: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 0: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 5: [2022-11-24 14:57:09,175] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +19: [2022-11-24 14:57:09,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +22: [2022-11-24 14:57:09,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:57:09,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +27: [2022-11-24 14:57:09,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:57:09,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 14:57:09,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +10: [2022-11-24 14:57:09,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +19: [2022-11-24 14:57:09,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +22: [2022-11-24 14:57:09,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +30: [2022-11-24 14:57:09,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:57:09,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 8: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +17: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +15: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +16: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 8: [2022-11-24 14:57:09,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:57:09,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:57:09,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +27: [2022-11-24 14:57:09,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:57:09,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:57:09,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +31: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +28: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +20: [2022-11-24 14:57:09,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +10: [2022-11-24 14:57:09,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +19: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +22: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +30: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:57:09,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:57:09,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 14:57:09,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:57:09,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +16: [2022-11-24 14:57:09,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:57:09,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:57:09,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +27: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:57:09,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +15: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 7: [2022-11-24 14:57:09,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:57:09,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:57:09,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +31: [2022-11-24 14:57:09,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 14:57:09,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +28: [2022-11-24 14:57:09,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:57:09,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +23: [2022-11-24 14:57:09,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:57:09,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +20: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +10: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:57:09,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +22: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +30: [2022-11-24 14:57:09,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +19: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:57:09,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:57:09,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 8: [2022-11-24 14:57:09,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +17: [2022-11-24 14:57:09,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:57:09,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +16: [2022-11-24 14:57:09,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:57:09,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:57:09,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +27: [2022-11-24 14:57:09,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 7: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:57:09,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +31: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +28: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:57:09,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +20: [2022-11-24 14:57:09,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:57:09,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +10: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +19: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +22: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:57:09,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +30: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:57:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 8: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:57:09,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +16: [2022-11-24 14:57:09,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:57:09,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +27: [2022-11-24 14:57:09,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:57:09,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 7: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:57:09,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:57:09,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +14: [2022-11-24 14:57:09,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +31: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +28: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:57:09,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +20: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:57:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +10: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +22: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +19: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +30: [2022-11-24 14:57:09,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:57:09,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 8: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 8: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +16: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:57:09,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:57:09,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +27: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 7: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:57:09,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:57:09,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +31: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +28: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:57:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +23: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +20: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +10: [2022-11-24 14:57:09,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:57:09,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:57:09,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +22: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +19: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +19: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:57:09,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 14:57:09,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:57:09,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:57:09,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +17: [2022-11-24 14:57:09,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:57:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 7: [2022-11-24 14:57:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +27: [2022-11-24 14:57:09,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:57:09,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +15: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. + 5: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +18: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +31: [2022-11-24 14:57:09,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +31: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:57:09,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:57:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +23: [2022-11-24 14:57:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +20: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +10: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +20: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +20: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +11: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +30: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +11: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +14: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +22: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +14: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 0: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +27: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 0: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +23: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 9: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +31: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt + 5: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +30: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +19: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +22: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 3: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +13: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +24: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +17: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 9: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +12: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +31: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +10: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +15: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 7: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +23: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +23: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +17: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 9: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +29: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +31: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 5: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +28: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +27: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +10: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +30: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 3: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 8: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 8: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. + 4: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 4: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +15: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +21: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 7: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +18: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +12: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +28: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +28: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +25: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +30: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +16: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +19: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 2: [2022-11-24 14:57:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 3: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +13: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +24: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +21: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +12: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +29: [2022-11-24 14:57:09,233] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +16: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +16: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 6: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +13: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +24: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +21: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +29: [2022-11-24 14:57:09,233] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 2: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 6: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +18: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 1: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 14:57:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 14:57:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,234] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step13000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! +26: [2022-11-24 14:57:09,234] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step13000 is ready now! + 0: successfully saved checkpoint at iteration 13000 to checkpoints_83m +31: time (ms) | save-checkpoint: 325.74 +31: iteration 13010/ 37905 | consumed samples: 3330560 | consumed tokens: 6820986880 | elapsed time per iteration (s): 0.22 | learning rate: 1.526E-04 | global batch size: 256 | lm loss: 3.024041E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.538 | TFLOPs: 7.44 | +31: iteration 13020/ 37905 | consumed samples: 3333120 | consumed tokens: 6826229760 | elapsed time per iteration (s): 0.20 | learning rate: 1.525E-04 | global batch size: 256 | lm loss: 2.998723E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.838 | TFLOPs: 8.11 | +31: iteration 13030/ 37905 | consumed samples: 3335680 | consumed tokens: 6831472640 | elapsed time per iteration (s): 0.22 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 2.987284E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.166 | TFLOPs: 7.48 | +31: iteration 13040/ 37905 | consumed samples: 3338240 | consumed tokens: 6836715520 | elapsed time per iteration (s): 0.23 | learning rate: 1.524E-04 | global batch size: 256 | lm loss: 3.015627E+00 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.758 | TFLOPs: 7.02 | +31: iteration 13050/ 37905 | consumed samples: 3340800 | consumed tokens: 6841958400 | elapsed time per iteration (s): 0.22 | learning rate: 1.523E-04 | global batch size: 256 | lm loss: 2.964171E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.016 | TFLOPs: 7.54 | +31: iteration 13060/ 37905 | consumed samples: 3343360 | consumed tokens: 6847201280 | elapsed time per iteration (s): 0.19 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 2.998570E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.261 | TFLOPs: 8.45 | +31: iteration 13070/ 37905 | consumed samples: 3345920 | consumed tokens: 6852444160 | elapsed time per iteration (s): 0.19 | learning rate: 1.522E-04 | global batch size: 256 | lm loss: 3.024177E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.582 | TFLOPs: 8.37 | +31: iteration 13080/ 37905 | consumed samples: 3348480 | consumed tokens: 6857687040 | elapsed time per iteration (s): 0.19 | learning rate: 1.521E-04 | global batch size: 256 | lm loss: 3.032802E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1368.925 | TFLOPs: 8.72 | +31: iteration 13090/ 37905 | consumed samples: 3351040 | consumed tokens: 6862929920 | elapsed time per iteration (s): 0.19 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 3.005128E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1348.714 | TFLOPs: 8.59 | +31: iteration 13100/ 37905 | consumed samples: 3353600 | consumed tokens: 6868172800 | elapsed time per iteration (s): 0.20 | learning rate: 1.520E-04 | global batch size: 256 | lm loss: 3.037695E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.023 | TFLOPs: 8.11 | +31: iteration 13110/ 37905 | consumed samples: 3356160 | consumed tokens: 6873415680 | elapsed time per iteration (s): 0.19 | learning rate: 1.519E-04 | global batch size: 256 | lm loss: 3.004264E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.035 | TFLOPs: 8.44 | +31: iteration 13120/ 37905 | consumed samples: 3358720 | consumed tokens: 6878658560 | elapsed time per iteration (s): 0.19 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 3.015637E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.019 | TFLOPs: 8.53 | +31: iteration 13130/ 37905 | consumed samples: 3361280 | consumed tokens: 6883901440 | elapsed time per iteration (s): 0.18 | learning rate: 1.518E-04 | global batch size: 256 | lm loss: 2.982483E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1408.199 | TFLOPs: 8.97 | +31: iteration 13140/ 37905 | consumed samples: 3363840 | consumed tokens: 6889144320 | elapsed time per iteration (s): 0.20 | learning rate: 1.517E-04 | global batch size: 256 | lm loss: 2.962353E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.955 | TFLOPs: 8.07 | +31: iteration 13150/ 37905 | consumed samples: 3366400 | consumed tokens: 6894387200 | elapsed time per iteration (s): 0.19 | learning rate: 1.516E-04 | global batch size: 256 | lm loss: 3.012358E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1337.460 | TFLOPs: 8.52 | +31: iteration 13160/ 37905 | consumed samples: 3368960 | consumed tokens: 6899630080 | elapsed time per iteration (s): 0.22 | learning rate: 1.516E-04 | global batch size: 256 | lm loss: 3.015127E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.072 | TFLOPs: 7.40 | +31: iteration 13170/ 37905 | consumed samples: 3371520 | consumed tokens: 6904872960 | elapsed time per iteration (s): 0.20 | learning rate: 1.515E-04 | global batch size: 256 | lm loss: 3.006483E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.064 | TFLOPs: 8.18 | +31: iteration 13180/ 37905 | consumed samples: 3374080 | consumed tokens: 6910115840 | elapsed time per iteration (s): 0.27 | learning rate: 1.514E-04 | global batch size: 256 | lm loss: 2.972042E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 937.588 | TFLOPs: 5.97 | +31: iteration 13190/ 37905 | consumed samples: 3376640 | consumed tokens: 6915358720 | elapsed time per iteration (s): 0.22 | learning rate: 1.514E-04 | global batch size: 256 | lm loss: 3.016376E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.689 | TFLOPs: 7.28 | +31: iteration 13200/ 37905 | consumed samples: 3379200 | consumed tokens: 6920601600 | elapsed time per iteration (s): 0.22 | learning rate: 1.513E-04 | global batch size: 256 | lm loss: 3.005549E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.330 | TFLOPs: 7.47 | +31: iteration 13210/ 37905 | consumed samples: 3381760 | consumed tokens: 6925844480 | elapsed time per iteration (s): 0.25 | learning rate: 1.512E-04 | global batch size: 256 | lm loss: 2.967887E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.471 | TFLOPs: 6.60 | +31: iteration 13220/ 37905 | consumed samples: 3384320 | consumed tokens: 6931087360 | elapsed time per iteration (s): 0.24 | learning rate: 1.512E-04 | global batch size: 256 | lm loss: 3.028110E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.911 | TFLOPs: 6.88 | +31: iteration 13230/ 37905 | consumed samples: 3386880 | consumed tokens: 6936330240 | elapsed time per iteration (s): 0.23 | learning rate: 1.511E-04 | global batch size: 256 | lm loss: 3.017630E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.472 | TFLOPs: 7.21 | +31: iteration 13240/ 37905 | consumed samples: 3389440 | consumed tokens: 6941573120 | elapsed time per iteration (s): 0.21 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 3.012486E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.438 | TFLOPs: 7.77 | +31: iteration 13250/ 37905 | consumed samples: 3392000 | consumed tokens: 6946816000 | elapsed time per iteration (s): 0.21 | learning rate: 1.510E-04 | global batch size: 256 | lm loss: 3.018495E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.324 | TFLOPs: 7.92 | +31: iteration 13260/ 37905 | consumed samples: 3394560 | consumed tokens: 6952058880 | elapsed time per iteration (s): 0.24 | learning rate: 1.509E-04 | global batch size: 256 | lm loss: 3.026385E+00 | grad norm: 0.330 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.305 | TFLOPs: 6.73 | +31: iteration 13270/ 37905 | consumed samples: 3397120 | consumed tokens: 6957301760 | elapsed time per iteration (s): 0.23 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 3.021942E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.940 | TFLOPs: 7.20 | +31: iteration 13280/ 37905 | consumed samples: 3399680 | consumed tokens: 6962544640 | elapsed time per iteration (s): 0.23 | learning rate: 1.508E-04 | global batch size: 256 | lm loss: 2.973779E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1137.004 | TFLOPs: 7.24 | +31: iteration 13290/ 37905 | consumed samples: 3402240 | consumed tokens: 6967787520 | elapsed time per iteration (s): 0.23 | learning rate: 1.507E-04 | global batch size: 256 | lm loss: 3.031567E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.265 | TFLOPs: 6.99 | +31: iteration 13300/ 37905 | consumed samples: 3404800 | consumed tokens: 6973030400 | elapsed time per iteration (s): 0.22 | learning rate: 1.506E-04 | global batch size: 256 | lm loss: 3.017650E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.326 | TFLOPs: 7.45 | +31: iteration 13310/ 37905 | consumed samples: 3407360 | consumed tokens: 6978273280 | elapsed time per iteration (s): 0.25 | learning rate: 1.506E-04 | global batch size: 256 | lm loss: 3.021998E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.192 | TFLOPs: 6.43 | +31: iteration 13320/ 37905 | consumed samples: 3409920 | consumed tokens: 6983516160 | elapsed time per iteration (s): 0.21 | learning rate: 1.505E-04 | global batch size: 256 | lm loss: 3.004095E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.257 | TFLOPs: 7.78 | +31: iteration 13330/ 37905 | consumed samples: 3412480 | consumed tokens: 6988759040 | elapsed time per iteration (s): 0.21 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 2.995269E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.172 | TFLOPs: 7.78 | +31: iteration 13340/ 37905 | consumed samples: 3415040 | consumed tokens: 6994001920 | elapsed time per iteration (s): 0.24 | learning rate: 1.504E-04 | global batch size: 256 | lm loss: 3.003524E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.748 | TFLOPs: 6.91 | +31: iteration 13350/ 37905 | consumed samples: 3417600 | consumed tokens: 6999244800 | elapsed time per iteration (s): 0.23 | learning rate: 1.503E-04 | global batch size: 256 | lm loss: 2.993832E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.860 | TFLOPs: 6.99 | +31: iteration 13360/ 37905 | consumed samples: 3420160 | consumed tokens: 7004487680 | elapsed time per iteration (s): 0.21 | learning rate: 1.502E-04 | global batch size: 256 | lm loss: 3.007299E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.480 | TFLOPs: 7.84 | +31: iteration 13370/ 37905 | consumed samples: 3422720 | consumed tokens: 7009730560 | elapsed time per iteration (s): 0.24 | learning rate: 1.502E-04 | global batch size: 256 | lm loss: 3.003834E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.444 | TFLOPs: 6.81 | +31: iteration 13380/ 37905 | consumed samples: 3425280 | consumed tokens: 7014973440 | elapsed time per iteration (s): 0.24 | learning rate: 1.501E-04 | global batch size: 256 | lm loss: 2.993323E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.782 | TFLOPs: 6.71 | +31: iteration 13390/ 37905 | consumed samples: 3427840 | consumed tokens: 7020216320 | elapsed time per iteration (s): 0.22 | learning rate: 1.500E-04 | global batch size: 256 | lm loss: 3.004275E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.374 | TFLOPs: 7.52 | +31: iteration 13400/ 37905 | consumed samples: 3430400 | consumed tokens: 7025459200 | elapsed time per iteration (s): 0.23 | learning rate: 1.500E-04 | global batch size: 256 | lm loss: 3.007168E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.252 | TFLOPs: 7.16 | +31: iteration 13410/ 37905 | consumed samples: 3432960 | consumed tokens: 7030702080 | elapsed time per iteration (s): 0.22 | learning rate: 1.499E-04 | global batch size: 256 | lm loss: 3.034369E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.007 | TFLOPs: 7.34 | +31: iteration 13420/ 37905 | consumed samples: 3435520 | consumed tokens: 7035944960 | elapsed time per iteration (s): 0.21 | learning rate: 1.498E-04 | global batch size: 256 | lm loss: 3.051720E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.701 | TFLOPs: 7.70 | +31: iteration 13430/ 37905 | consumed samples: 3438080 | consumed tokens: 7041187840 | elapsed time per iteration (s): 0.21 | learning rate: 1.498E-04 | global batch size: 256 | lm loss: 2.989276E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.148 | TFLOPs: 7.73 | +31: iteration 13440/ 37905 | consumed samples: 3440640 | consumed tokens: 7046430720 | elapsed time per iteration (s): 0.20 | learning rate: 1.497E-04 | global batch size: 256 | lm loss: 3.000077E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.828 | TFLOPs: 8.10 | +31: iteration 13450/ 37905 | consumed samples: 3443200 | consumed tokens: 7051673600 | elapsed time per iteration (s): 0.21 | learning rate: 1.496E-04 | global batch size: 256 | lm loss: 3.020189E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.935 | TFLOPs: 7.92 | +31: iteration 13460/ 37905 | consumed samples: 3445760 | consumed tokens: 7056916480 | elapsed time per iteration (s): 0.20 | learning rate: 1.496E-04 | global batch size: 256 | lm loss: 3.030836E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.647 | TFLOPs: 8.25 | +31: iteration 13470/ 37905 | consumed samples: 3448320 | consumed tokens: 7062159360 | elapsed time per iteration (s): 0.24 | learning rate: 1.495E-04 | global batch size: 256 | lm loss: 2.971501E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.627 | TFLOPs: 6.88 | +31: iteration 13480/ 37905 | consumed samples: 3450880 | consumed tokens: 7067402240 | elapsed time per iteration (s): 0.22 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 2.998463E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.316 | TFLOPs: 7.38 | +31: iteration 13490/ 37905 | consumed samples: 3453440 | consumed tokens: 7072645120 | elapsed time per iteration (s): 0.23 | learning rate: 1.494E-04 | global batch size: 256 | lm loss: 2.985583E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.310 | TFLOPs: 7.17 | +31: iteration 13500/ 37905 | consumed samples: 3456000 | consumed tokens: 7077888000 | elapsed time per iteration (s): 0.25 | learning rate: 1.493E-04 | global batch size: 256 | lm loss: 2.976590E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.020 | TFLOPs: 6.55 | +31: iteration 13510/ 37905 | consumed samples: 3458560 | consumed tokens: 7083130880 | elapsed time per iteration (s): 0.20 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 3.025101E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1285.704 | TFLOPs: 8.19 | +31: iteration 13520/ 37905 | consumed samples: 3461120 | consumed tokens: 7088373760 | elapsed time per iteration (s): 0.22 | learning rate: 1.492E-04 | global batch size: 256 | lm loss: 3.026154E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.588 | TFLOPs: 7.49 | +31: iteration 13530/ 37905 | consumed samples: 3463680 | consumed tokens: 7093616640 | elapsed time per iteration (s): 0.20 | learning rate: 1.491E-04 | global batch size: 256 | lm loss: 2.990849E+00 | grad norm: 0.341 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1285.751 | TFLOPs: 8.19 | +31: iteration 13540/ 37905 | consumed samples: 3466240 | consumed tokens: 7098859520 | elapsed time per iteration (s): 0.21 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.034028E+00 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.313 | TFLOPs: 7.60 | +31: iteration 13550/ 37905 | consumed samples: 3468800 | consumed tokens: 7104102400 | elapsed time per iteration (s): 0.24 | learning rate: 1.490E-04 | global batch size: 256 | lm loss: 3.011494E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.916 | TFLOPs: 6.67 | +31: iteration 13560/ 37905 | consumed samples: 3471360 | consumed tokens: 7109345280 | elapsed time per iteration (s): 0.26 | learning rate: 1.489E-04 | global batch size: 256 | lm loss: 2.994726E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 988.242 | TFLOPs: 6.29 | +31: iteration 13570/ 37905 | consumed samples: 3473920 | consumed tokens: 7114588160 | elapsed time per iteration (s): 0.25 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 3.020616E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1005.124 | TFLOPs: 6.40 | +31: iteration 13580/ 37905 | consumed samples: 3476480 | consumed tokens: 7119831040 | elapsed time per iteration (s): 0.22 | learning rate: 1.488E-04 | global batch size: 256 | lm loss: 3.004167E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.773 | TFLOPs: 7.27 | +31: iteration 13590/ 37905 | consumed samples: 3479040 | consumed tokens: 7125073920 | elapsed time per iteration (s): 0.22 | learning rate: 1.487E-04 | global batch size: 256 | lm loss: 2.987804E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.450 | TFLOPs: 7.55 | +31: iteration 13600/ 37905 | consumed samples: 3481600 | consumed tokens: 7130316800 | elapsed time per iteration (s): 0.25 | learning rate: 1.486E-04 | global batch size: 256 | lm loss: 3.052081E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.352 | TFLOPs: 6.53 | +31: iteration 13610/ 37905 | consumed samples: 3484160 | consumed tokens: 7135559680 | elapsed time per iteration (s): 0.21 | learning rate: 1.486E-04 | global batch size: 256 | lm loss: 3.010899E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.043 | TFLOPs: 7.66 | +31: iteration 13620/ 37905 | consumed samples: 3486720 | consumed tokens: 7140802560 | elapsed time per iteration (s): 0.20 | learning rate: 1.485E-04 | global batch size: 256 | lm loss: 2.983395E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.790 | TFLOPs: 8.02 | +31: iteration 13630/ 37905 | consumed samples: 3489280 | consumed tokens: 7146045440 | elapsed time per iteration (s): 0.20 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 3.009463E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.679 | TFLOPs: 8.25 | +31: iteration 13640/ 37905 | consumed samples: 3491840 | consumed tokens: 7151288320 | elapsed time per iteration (s): 0.21 | learning rate: 1.484E-04 | global batch size: 256 | lm loss: 2.982849E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.814 | TFLOPs: 7.74 | +31: iteration 13650/ 37905 | consumed samples: 3494400 | consumed tokens: 7156531200 | elapsed time per iteration (s): 0.22 | learning rate: 1.483E-04 | global batch size: 256 | lm loss: 3.021428E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.061 | TFLOPs: 7.34 | +31: iteration 13660/ 37905 | consumed samples: 3496960 | consumed tokens: 7161774080 | elapsed time per iteration (s): 0.20 | learning rate: 1.482E-04 | global batch size: 256 | lm loss: 2.998615E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1308.613 | TFLOPs: 8.33 | +31: iteration 13670/ 37905 | consumed samples: 3499520 | consumed tokens: 7167016960 | elapsed time per iteration (s): 0.23 | learning rate: 1.482E-04 | global batch size: 256 | lm loss: 3.032550E+00 | grad norm: 0.335 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.596 | TFLOPs: 7.23 | +31: iteration 13680/ 37905 | consumed samples: 3502080 | consumed tokens: 7172259840 | elapsed time per iteration (s): 0.21 | learning rate: 1.481E-04 | global batch size: 256 | lm loss: 2.985399E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.472 | TFLOPs: 7.68 | +31: iteration 13690/ 37905 | consumed samples: 3504640 | consumed tokens: 7177502720 | elapsed time per iteration (s): 0.22 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 3.019893E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.004 | TFLOPs: 7.46 | +31: iteration 13700/ 37905 | consumed samples: 3507200 | consumed tokens: 7182745600 | elapsed time per iteration (s): 0.23 | learning rate: 1.480E-04 | global batch size: 256 | lm loss: 3.038583E+00 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.070 | TFLOPs: 6.99 | +31: iteration 13710/ 37905 | consumed samples: 3509760 | consumed tokens: 7187988480 | elapsed time per iteration (s): 0.21 | learning rate: 1.479E-04 | global batch size: 256 | lm loss: 3.000051E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.658 | TFLOPs: 7.61 | +31: iteration 13720/ 37905 | consumed samples: 3512320 | consumed tokens: 7193231360 | elapsed time per iteration (s): 0.22 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 2.976433E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.348 | TFLOPs: 7.54 | +31: iteration 13730/ 37905 | consumed samples: 3514880 | consumed tokens: 7198474240 | elapsed time per iteration (s): 0.21 | learning rate: 1.478E-04 | global batch size: 256 | lm loss: 3.013026E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.248 | TFLOPs: 7.80 | +31: iteration 13740/ 37905 | consumed samples: 3517440 | consumed tokens: 7203717120 | elapsed time per iteration (s): 0.21 | learning rate: 1.477E-04 | global batch size: 256 | lm loss: 3.016697E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.793 | TFLOPs: 7.62 | +31: iteration 13750/ 37905 | consumed samples: 3520000 | consumed tokens: 7208960000 | elapsed time per iteration (s): 0.20 | learning rate: 1.476E-04 | global batch size: 256 | lm loss: 3.016302E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.593 | TFLOPs: 8.09 | +31: iteration 13760/ 37905 | consumed samples: 3522560 | consumed tokens: 7214202880 | elapsed time per iteration (s): 0.20 | learning rate: 1.475E-04 | global batch size: 256 | lm loss: 2.976627E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.260 | TFLOPs: 8.05 | +31: iteration 13770/ 37905 | consumed samples: 3525120 | consumed tokens: 7219445760 | elapsed time per iteration (s): 0.20 | learning rate: 1.475E-04 | global batch size: 256 | lm loss: 3.048380E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.576 | TFLOPs: 8.36 | +31: iteration 13780/ 37905 | consumed samples: 3527680 | consumed tokens: 7224688640 | elapsed time per iteration (s): 0.19 | learning rate: 1.474E-04 | global batch size: 256 | lm loss: 2.983603E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1380.287 | TFLOPs: 8.79 | +31: iteration 13790/ 37905 | consumed samples: 3530240 | consumed tokens: 7229931520 | elapsed time per iteration (s): 0.23 | learning rate: 1.473E-04 | global batch size: 256 | lm loss: 3.016478E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.270 | TFLOPs: 6.99 | +31: iteration 13800/ 37905 | consumed samples: 3532800 | consumed tokens: 7235174400 | elapsed time per iteration (s): 0.21 | learning rate: 1.473E-04 | global batch size: 256 | lm loss: 3.023269E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.552 | TFLOPs: 7.75 | +31: iteration 13810/ 37905 | consumed samples: 3535360 | consumed tokens: 7240417280 | elapsed time per iteration (s): 0.22 | learning rate: 1.472E-04 | global batch size: 256 | lm loss: 2.979029E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.767 | TFLOPs: 7.49 | +31: iteration 13820/ 37905 | consumed samples: 3537920 | consumed tokens: 7245660160 | elapsed time per iteration (s): 0.23 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 3.000006E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.445 | TFLOPs: 7.15 | +31: iteration 13830/ 37905 | consumed samples: 3540480 | consumed tokens: 7250903040 | elapsed time per iteration (s): 0.22 | learning rate: 1.471E-04 | global batch size: 256 | lm loss: 3.027150E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.543 | TFLOPs: 7.44 | +31: iteration 13840/ 37905 | consumed samples: 3543040 | consumed tokens: 7256145920 | elapsed time per iteration (s): 0.22 | learning rate: 1.470E-04 | global batch size: 256 | lm loss: 2.987668E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.231 | TFLOPs: 7.48 | +31: iteration 13850/ 37905 | consumed samples: 3545600 | consumed tokens: 7261388800 | elapsed time per iteration (s): 0.23 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 3.010934E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.704 | TFLOPs: 7.18 | +31: iteration 13860/ 37905 | consumed samples: 3548160 | consumed tokens: 7266631680 | elapsed time per iteration (s): 0.26 | learning rate: 1.469E-04 | global batch size: 256 | lm loss: 3.050862E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 977.163 | TFLOPs: 6.22 | +31: iteration 13870/ 37905 | consumed samples: 3550720 | consumed tokens: 7271874560 | elapsed time per iteration (s): 0.20 | learning rate: 1.468E-04 | global batch size: 256 | lm loss: 3.015154E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.490 | TFLOPs: 8.00 | +31: iteration 13880/ 37905 | consumed samples: 3553280 | consumed tokens: 7277117440 | elapsed time per iteration (s): 0.23 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 2.965334E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.341 | TFLOPs: 7.03 | +31: iteration 13890/ 37905 | consumed samples: 3555840 | consumed tokens: 7282360320 | elapsed time per iteration (s): 0.27 | learning rate: 1.467E-04 | global batch size: 256 | lm loss: 2.996252E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 944.887 | TFLOPs: 6.02 | +31: iteration 13900/ 37905 | consumed samples: 3558400 | consumed tokens: 7287603200 | elapsed time per iteration (s): 0.20 | learning rate: 1.466E-04 | global batch size: 256 | lm loss: 2.973201E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.721 | TFLOPs: 8.09 | +31: iteration 13910/ 37905 | consumed samples: 3560960 | consumed tokens: 7292846080 | elapsed time per iteration (s): 0.21 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 3.014358E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.676 | TFLOPs: 7.90 | +31: iteration 13920/ 37905 | consumed samples: 3563520 | consumed tokens: 7298088960 | elapsed time per iteration (s): 0.20 | learning rate: 1.465E-04 | global batch size: 256 | lm loss: 2.986777E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.530 | TFLOPs: 8.14 | +31: iteration 13930/ 37905 | consumed samples: 3566080 | consumed tokens: 7303331840 | elapsed time per iteration (s): 0.20 | learning rate: 1.464E-04 | global batch size: 256 | lm loss: 2.997690E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.314 | TFLOPs: 8.05 | +31: iteration 13940/ 37905 | consumed samples: 3568640 | consumed tokens: 7308574720 | elapsed time per iteration (s): 0.22 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 3.032701E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.294 | TFLOPs: 7.52 | +31: iteration 13950/ 37905 | consumed samples: 3571200 | consumed tokens: 7313817600 | elapsed time per iteration (s): 0.21 | learning rate: 1.463E-04 | global batch size: 256 | lm loss: 3.020105E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.803 | TFLOPs: 7.95 | +31: iteration 13960/ 37905 | consumed samples: 3573760 | consumed tokens: 7319060480 | elapsed time per iteration (s): 0.24 | learning rate: 1.462E-04 | global batch size: 256 | lm loss: 3.004913E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.780 | TFLOPs: 6.76 | +31: iteration 13970/ 37905 | consumed samples: 3576320 | consumed tokens: 7324303360 | elapsed time per iteration (s): 0.20 | learning rate: 1.461E-04 | global batch size: 256 | lm loss: 2.985645E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1284.750 | TFLOPs: 8.18 | +31: iteration 13980/ 37905 | consumed samples: 3578880 | consumed tokens: 7329546240 | elapsed time per iteration (s): 0.24 | learning rate: 1.461E-04 | global batch size: 256 | lm loss: 3.009472E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.714 | TFLOPs: 6.70 | +31: iteration 13990/ 37905 | consumed samples: 3581440 | consumed tokens: 7334789120 | elapsed time per iteration (s): 0.21 | learning rate: 1.460E-04 | global batch size: 256 | lm loss: 2.963804E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.928 | TFLOPs: 7.66 | + 0: [2022-11-24 15:00:46,817] [INFO] [logging.py:68:log_dist] [Rank 0] step=14000, skipped=0, lr=[0.00014591355890008223, 0.00014591355890008223, 0.00014591355890008223], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 14000/ 37905 | consumed samples: 3584000 | consumed tokens: 7340032000 | elapsed time per iteration (s): 0.22 | learning rate: 1.459E-04 | global batch size: 256 | lm loss: 2.972773E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.315 | TFLOPs: 7.39 | + 0: steps: 14000 loss: 2.9985 iter time (s): 0.204 samples/sec: 1256.269 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 14000 | lm loss value: 2.888467E+00 | lm loss PPL: 1.796574E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 14000 to checkpoints_83m + 0: [2022-11-24 15:00:46,916] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step14000 is begin to save! + 0: [2022-11-24 15:00:46,926] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:00:46,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:00:46,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,009] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,020] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,044] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,055] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,066] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,077] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,088] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:00:47,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:00:47,111] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step14000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:00:47,111] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:00:47,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:00:47,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step14000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:00:47,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:00:47,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:00:47,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 3: [2022-11-24 15:00:47,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:00:47,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:00:47,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:00:47,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:00:47,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +25: [2022-11-24 15:00:47,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:00:47,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +18: [2022-11-24 15:00:47,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +16: [2022-11-24 15:00:47,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:00:47,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:00:47,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 15:00:47,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +19: [2022-11-24 15:00:47,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 5: [2022-11-24 15:00:47,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:00:47,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 3: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:00:47,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 6: [2022-11-24 15:00:47,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:00:47,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 9: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +31: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +20: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +10: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:00:47,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +10: [2022-11-24 15:00:47,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 4: [2022-11-24 15:00:47,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 4: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:00:47,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:00:47,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:00:47,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 7: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:00:47,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:00:47,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +14: [2022-11-24 15:00:47,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +28: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +18: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:00:47,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +16: [2022-11-24 15:00:47,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:00:47,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +19: [2022-11-24 15:00:47,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:00:47,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:00:47,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 6: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 3: [2022-11-24 15:00:47,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:00:47,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 5: [2022-11-24 15:00:47,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:00:47,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:00:47,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:00:47,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:00:47,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 9: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 9: [2022-11-24 15:00:47,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 7: [2022-11-24 15:00:47,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:00:47,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:00:47,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:00:47,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +18: [2022-11-24 15:00:47,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:00:47,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:00:47,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +16: [2022-11-24 15:00:47,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:00:47,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +19: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:00:47,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 5: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 3: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 6: [2022-11-24 15:00:47,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +31: [2022-11-24 15:00:47,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +13: [2022-11-24 15:00:47,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +10: [2022-11-24 15:00:47,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:00:47,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:00:47,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 4: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:00:47,205] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:00:47,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 7: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +20: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,206] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 9: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +28: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:00:47,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +18: [2022-11-24 15:00:47,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:00:47,207] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +16: [2022-11-24 15:00:47,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:00:47,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,208] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:00:47,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:00:47,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +19: [2022-11-24 15:00:47,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,209] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:00:47,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 3: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 6: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,210] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:00:47,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,210] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +10: [2022-11-24 15:00:47,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 4: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:00:47,211] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:00:47,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:00:47,212] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +20: [2022-11-24 15:00:47,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 7: [2022-11-24 15:00:47,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,213] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,213] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:00:47,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +18: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +16: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:00:47,214] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:00:47,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +19: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:00:47,215] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:00:47,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 3: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 5: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,216] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,216] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 6: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +10: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:00:47,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,217] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:00:47,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 4: [2022-11-24 15:00:47,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:00:47,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:00:47,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:00:47,218] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 9: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +20: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,219] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 7: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:00:47,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:00:47,220] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:00:47,220] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +18: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +16: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,221] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:00:47,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +19: [2022-11-24 15:00:47,222] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:00:47,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 6: [2022-11-24 15:00:47,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,223] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:00:47,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 3: [2022-11-24 15:00:47,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 5: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,224] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:00:47,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:00:47,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +13: [2022-11-24 15:00:47,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 1: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:00:47,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 4: [2022-11-24 15:00:47,225] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,225] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +20: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 9: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:00:47,226] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 7: [2022-11-24 15:00:47,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,227] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,227] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:00:47,227] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:00:47,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:00:47,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +14: [2022-11-24 15:00:47,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,228] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:00:47,228] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,229] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +24: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:00:47,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +19: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,230] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +27: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +27: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 9: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +16: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +14: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 6: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 2: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +24: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +23: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +18: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +28: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +13: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +26: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 7: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +23: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +18: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +11: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +12: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +31: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +28: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +19: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +14: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +13: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +20: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +20: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +26: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +11: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +12: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +25: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +10: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +10: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +22: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +21: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 5: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +22: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +14: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +15: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +17: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +29: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +30: [2022-11-24 15:00:47,231] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 8: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +15: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,232] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step14000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +17: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +29: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 5: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +30: [2022-11-24 15:00:47,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! +21: [2022-11-24 15:00:47,232] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step14000 is ready now! + 0: successfully saved checkpoint at iteration 14000 to checkpoints_83m +31: time (ms) | save-checkpoint: 321.00 +31: iteration 14010/ 37905 | consumed samples: 3586560 | consumed tokens: 7345274880 | elapsed time per iteration (s): 0.29 | learning rate: 1.458E-04 | global batch size: 256 | lm loss: 3.045868E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 872.600 | TFLOPs: 5.56 | +31: iteration 14020/ 37905 | consumed samples: 3589120 | consumed tokens: 7350517760 | elapsed time per iteration (s): 0.26 | learning rate: 1.458E-04 | global batch size: 256 | lm loss: 3.009868E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.355 | TFLOPs: 6.28 | +31: iteration 14030/ 37905 | consumed samples: 3591680 | consumed tokens: 7355760640 | elapsed time per iteration (s): 0.21 | learning rate: 1.457E-04 | global batch size: 256 | lm loss: 3.023905E+00 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.790 | TFLOPs: 7.75 | +31: iteration 14040/ 37905 | consumed samples: 3594240 | consumed tokens: 7361003520 | elapsed time per iteration (s): 0.21 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 2.988329E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.818 | TFLOPs: 7.71 | +31: iteration 14050/ 37905 | consumed samples: 3596800 | consumed tokens: 7366246400 | elapsed time per iteration (s): 0.22 | learning rate: 1.456E-04 | global batch size: 256 | lm loss: 2.971392E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.920 | TFLOPs: 7.26 | +31: iteration 14060/ 37905 | consumed samples: 3599360 | consumed tokens: 7371489280 | elapsed time per iteration (s): 0.21 | learning rate: 1.455E-04 | global batch size: 256 | lm loss: 2.985180E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.195 | TFLOPs: 7.60 | +31: iteration 14070/ 37905 | consumed samples: 3601920 | consumed tokens: 7376732160 | elapsed time per iteration (s): 0.23 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 2.961036E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.863 | TFLOPs: 7.14 | +31: iteration 14080/ 37905 | consumed samples: 3604480 | consumed tokens: 7381975040 | elapsed time per iteration (s): 0.23 | learning rate: 1.454E-04 | global batch size: 256 | lm loss: 3.010462E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1136.688 | TFLOPs: 7.24 | +31: iteration 14090/ 37905 | consumed samples: 3607040 | consumed tokens: 7387217920 | elapsed time per iteration (s): 0.21 | learning rate: 1.453E-04 | global batch size: 256 | lm loss: 2.968681E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.893 | TFLOPs: 7.95 | +31: iteration 14100/ 37905 | consumed samples: 3609600 | consumed tokens: 7392460800 | elapsed time per iteration (s): 0.21 | learning rate: 1.452E-04 | global batch size: 256 | lm loss: 3.006091E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.022 | TFLOPs: 7.71 | +31: iteration 14110/ 37905 | consumed samples: 3612160 | consumed tokens: 7397703680 | elapsed time per iteration (s): 0.22 | learning rate: 1.452E-04 | global batch size: 256 | lm loss: 3.006851E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.863 | TFLOPs: 7.44 | +31: iteration 14120/ 37905 | consumed samples: 3614720 | consumed tokens: 7402946560 | elapsed time per iteration (s): 0.21 | learning rate: 1.451E-04 | global batch size: 256 | lm loss: 3.010528E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.661 | TFLOPs: 7.77 | +31: iteration 14130/ 37905 | consumed samples: 3617280 | consumed tokens: 7408189440 | elapsed time per iteration (s): 0.22 | learning rate: 1.450E-04 | global batch size: 256 | lm loss: 3.028406E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.966 | TFLOPs: 7.39 | +31: iteration 14140/ 37905 | consumed samples: 3619840 | consumed tokens: 7413432320 | elapsed time per iteration (s): 0.21 | learning rate: 1.450E-04 | global batch size: 256 | lm loss: 2.984904E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.748 | TFLOPs: 7.92 | +31: iteration 14150/ 37905 | consumed samples: 3622400 | consumed tokens: 7418675200 | elapsed time per iteration (s): 0.24 | learning rate: 1.449E-04 | global batch size: 256 | lm loss: 3.021193E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.696 | TFLOPs: 6.76 | +31: iteration 14160/ 37905 | consumed samples: 3624960 | consumed tokens: 7423918080 | elapsed time per iteration (s): 0.21 | learning rate: 1.448E-04 | global batch size: 256 | lm loss: 3.034609E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.921 | TFLOPs: 7.85 | +31: iteration 14170/ 37905 | consumed samples: 3627520 | consumed tokens: 7429160960 | elapsed time per iteration (s): 0.20 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 2.992017E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.346 | TFLOPs: 8.16 | +31: iteration 14180/ 37905 | consumed samples: 3630080 | consumed tokens: 7434403840 | elapsed time per iteration (s): 0.21 | learning rate: 1.447E-04 | global batch size: 256 | lm loss: 3.040052E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.639 | TFLOPs: 7.90 | +31: iteration 14190/ 37905 | consumed samples: 3632640 | consumed tokens: 7439646720 | elapsed time per iteration (s): 0.21 | learning rate: 1.446E-04 | global batch size: 256 | lm loss: 2.993950E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.442 | TFLOPs: 7.59 | +31: iteration 14200/ 37905 | consumed samples: 3635200 | consumed tokens: 7444889600 | elapsed time per iteration (s): 0.27 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 3.005990E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 943.832 | TFLOPs: 6.01 | +31: iteration 14210/ 37905 | consumed samples: 3637760 | consumed tokens: 7450132480 | elapsed time per iteration (s): 0.21 | learning rate: 1.445E-04 | global batch size: 256 | lm loss: 2.977899E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.453 | TFLOPs: 7.91 | +31: iteration 14220/ 37905 | consumed samples: 3640320 | consumed tokens: 7455375360 | elapsed time per iteration (s): 0.20 | learning rate: 1.444E-04 | global batch size: 256 | lm loss: 3.013598E+00 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.930 | TFLOPs: 8.32 | +31: iteration 14230/ 37905 | consumed samples: 3642880 | consumed tokens: 7460618240 | elapsed time per iteration (s): 0.21 | learning rate: 1.443E-04 | global batch size: 256 | lm loss: 2.986163E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.474 | TFLOPs: 7.87 | +31: iteration 14240/ 37905 | consumed samples: 3645440 | consumed tokens: 7465861120 | elapsed time per iteration (s): 0.21 | learning rate: 1.443E-04 | global batch size: 256 | lm loss: 3.017684E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.941 | TFLOPs: 7.69 | +31: iteration 14250/ 37905 | consumed samples: 3648000 | consumed tokens: 7471104000 | elapsed time per iteration (s): 0.27 | learning rate: 1.442E-04 | global batch size: 256 | lm loss: 3.013039E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 947.555 | TFLOPs: 6.03 | +31: iteration 14260/ 37905 | consumed samples: 3650560 | consumed tokens: 7476346880 | elapsed time per iteration (s): 0.19 | learning rate: 1.441E-04 | global batch size: 256 | lm loss: 3.026068E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1332.821 | TFLOPs: 8.49 | +31: iteration 14270/ 37905 | consumed samples: 3653120 | consumed tokens: 7481589760 | elapsed time per iteration (s): 0.26 | learning rate: 1.441E-04 | global batch size: 256 | lm loss: 2.976896E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 987.894 | TFLOPs: 6.29 | +31: iteration 14280/ 37905 | consumed samples: 3655680 | consumed tokens: 7486832640 | elapsed time per iteration (s): 0.25 | learning rate: 1.440E-04 | global batch size: 256 | lm loss: 2.994422E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.063 | TFLOPs: 6.62 | +31: iteration 14290/ 37905 | consumed samples: 3658240 | consumed tokens: 7492075520 | elapsed time per iteration (s): 0.23 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 3.013039E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.899 | TFLOPs: 7.06 | +31: iteration 14300/ 37905 | consumed samples: 3660800 | consumed tokens: 7497318400 | elapsed time per iteration (s): 0.23 | learning rate: 1.439E-04 | global batch size: 256 | lm loss: 2.940587E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.130 | TFLOPs: 7.13 | +31: iteration 14310/ 37905 | consumed samples: 3663360 | consumed tokens: 7502561280 | elapsed time per iteration (s): 0.22 | learning rate: 1.438E-04 | global batch size: 256 | lm loss: 2.954873E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.134 | TFLOPs: 7.51 | +31: iteration 14320/ 37905 | consumed samples: 3665920 | consumed tokens: 7507804160 | elapsed time per iteration (s): 0.21 | learning rate: 1.437E-04 | global batch size: 256 | lm loss: 2.960290E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.354 | TFLOPs: 7.62 | +31: iteration 14330/ 37905 | consumed samples: 3668480 | consumed tokens: 7513047040 | elapsed time per iteration (s): 0.21 | learning rate: 1.436E-04 | global batch size: 256 | lm loss: 2.974110E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.890 | TFLOPs: 7.86 | +31: iteration 14340/ 37905 | consumed samples: 3671040 | consumed tokens: 7518289920 | elapsed time per iteration (s): 0.21 | learning rate: 1.436E-04 | global batch size: 256 | lm loss: 2.999115E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.957 | TFLOPs: 7.77 | +31: iteration 14350/ 37905 | consumed samples: 3673600 | consumed tokens: 7523532800 | elapsed time per iteration (s): 0.21 | learning rate: 1.435E-04 | global batch size: 256 | lm loss: 3.025004E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.728 | TFLOPs: 7.67 | +31: iteration 14360/ 37905 | consumed samples: 3676160 | consumed tokens: 7528775680 | elapsed time per iteration (s): 0.22 | learning rate: 1.434E-04 | global batch size: 256 | lm loss: 3.032808E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.731 | TFLOPs: 7.44 | +31: iteration 14370/ 37905 | consumed samples: 3678720 | consumed tokens: 7534018560 | elapsed time per iteration (s): 0.22 | learning rate: 1.434E-04 | global batch size: 256 | lm loss: 3.029743E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.748 | TFLOPs: 7.33 | +31: iteration 14380/ 37905 | consumed samples: 3681280 | consumed tokens: 7539261440 | elapsed time per iteration (s): 0.22 | learning rate: 1.433E-04 | global batch size: 256 | lm loss: 2.977667E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.364 | TFLOPs: 7.52 | +31: iteration 14390/ 37905 | consumed samples: 3683840 | consumed tokens: 7544504320 | elapsed time per iteration (s): 0.22 | learning rate: 1.432E-04 | global batch size: 256 | lm loss: 3.009285E+00 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1155.200 | TFLOPs: 7.36 | +31: iteration 14400/ 37905 | consumed samples: 3686400 | consumed tokens: 7549747200 | elapsed time per iteration (s): 0.21 | learning rate: 1.432E-04 | global batch size: 256 | lm loss: 2.947833E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.642 | TFLOPs: 7.61 | +31: iteration 14410/ 37905 | consumed samples: 3688960 | consumed tokens: 7554990080 | elapsed time per iteration (s): 0.21 | learning rate: 1.431E-04 | global batch size: 256 | lm loss: 2.956166E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.736 | TFLOPs: 7.91 | +31: iteration 14420/ 37905 | consumed samples: 3691520 | consumed tokens: 7560232960 | elapsed time per iteration (s): 0.25 | learning rate: 1.430E-04 | global batch size: 256 | lm loss: 2.991537E+00 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.559 | TFLOPs: 6.52 | +31: iteration 14430/ 37905 | consumed samples: 3694080 | consumed tokens: 7565475840 | elapsed time per iteration (s): 0.23 | learning rate: 1.430E-04 | global batch size: 256 | lm loss: 3.000843E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.853 | TFLOPs: 7.00 | +31: iteration 14440/ 37905 | consumed samples: 3696640 | consumed tokens: 7570718720 | elapsed time per iteration (s): 0.21 | learning rate: 1.429E-04 | global batch size: 256 | lm loss: 2.963831E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.828 | TFLOPs: 7.76 | +31: iteration 14450/ 37905 | consumed samples: 3699200 | consumed tokens: 7575961600 | elapsed time per iteration (s): 0.23 | learning rate: 1.428E-04 | global batch size: 256 | lm loss: 2.976295E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.753 | TFLOPs: 7.11 | +31: iteration 14460/ 37905 | consumed samples: 3701760 | consumed tokens: 7581204480 | elapsed time per iteration (s): 0.25 | learning rate: 1.427E-04 | global batch size: 256 | lm loss: 3.008872E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.701 | TFLOPs: 6.56 | +31: iteration 14470/ 37905 | consumed samples: 3704320 | consumed tokens: 7586447360 | elapsed time per iteration (s): 0.21 | learning rate: 1.427E-04 | global batch size: 256 | lm loss: 3.012256E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.613 | TFLOPs: 7.91 | +31: iteration 14480/ 37905 | consumed samples: 3706880 | consumed tokens: 7591690240 | elapsed time per iteration (s): 0.22 | learning rate: 1.426E-04 | global batch size: 256 | lm loss: 2.976992E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.635 | TFLOPs: 7.32 | +31: iteration 14490/ 37905 | consumed samples: 3709440 | consumed tokens: 7596933120 | elapsed time per iteration (s): 0.24 | learning rate: 1.425E-04 | global batch size: 256 | lm loss: 2.975782E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.588 | TFLOPs: 6.84 | +31: iteration 14500/ 37905 | consumed samples: 3712000 | consumed tokens: 7602176000 | elapsed time per iteration (s): 0.23 | learning rate: 1.425E-04 | global batch size: 256 | lm loss: 2.987831E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.613 | TFLOPs: 7.02 | +31: iteration 14510/ 37905 | consumed samples: 3714560 | consumed tokens: 7607418880 | elapsed time per iteration (s): 0.24 | learning rate: 1.424E-04 | global batch size: 256 | lm loss: 3.008714E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.732 | TFLOPs: 6.71 | +31: iteration 14520/ 37905 | consumed samples: 3717120 | consumed tokens: 7612661760 | elapsed time per iteration (s): 0.20 | learning rate: 1.423E-04 | global batch size: 256 | lm loss: 3.051485E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.544 | TFLOPs: 8.25 | +31: iteration 14530/ 37905 | consumed samples: 3719680 | consumed tokens: 7617904640 | elapsed time per iteration (s): 0.26 | learning rate: 1.423E-04 | global batch size: 256 | lm loss: 2.984110E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 998.337 | TFLOPs: 6.36 | +31: iteration 14540/ 37905 | consumed samples: 3722240 | consumed tokens: 7623147520 | elapsed time per iteration (s): 0.22 | learning rate: 1.422E-04 | global batch size: 256 | lm loss: 3.002466E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.530 | TFLOPs: 7.46 | +31: iteration 14550/ 37905 | consumed samples: 3724800 | consumed tokens: 7628390400 | elapsed time per iteration (s): 0.22 | learning rate: 1.421E-04 | global batch size: 256 | lm loss: 2.966252E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.408 | TFLOPs: 7.45 | +31: iteration 14560/ 37905 | consumed samples: 3727360 | consumed tokens: 7633633280 | elapsed time per iteration (s): 0.25 | learning rate: 1.420E-04 | global batch size: 256 | lm loss: 2.982902E+00 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1006.053 | TFLOPs: 6.41 | +31: iteration 14570/ 37905 | consumed samples: 3729920 | consumed tokens: 7638876160 | elapsed time per iteration (s): 0.24 | learning rate: 1.420E-04 | global batch size: 256 | lm loss: 2.986802E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.794 | TFLOPs: 6.82 | +31: iteration 14580/ 37905 | consumed samples: 3732480 | consumed tokens: 7644119040 | elapsed time per iteration (s): 0.28 | learning rate: 1.419E-04 | global batch size: 256 | lm loss: 2.960067E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 908.076 | TFLOPs: 5.78 | +31: iteration 14590/ 37905 | consumed samples: 3735040 | consumed tokens: 7649361920 | elapsed time per iteration (s): 0.22 | learning rate: 1.418E-04 | global batch size: 256 | lm loss: 3.006198E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.537 | TFLOPs: 7.39 | +31: iteration 14600/ 37905 | consumed samples: 3737600 | consumed tokens: 7654604800 | elapsed time per iteration (s): 0.22 | learning rate: 1.418E-04 | global batch size: 256 | lm loss: 3.014439E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.628 | TFLOPs: 7.43 | +31: iteration 14610/ 37905 | consumed samples: 3740160 | consumed tokens: 7659847680 | elapsed time per iteration (s): 0.21 | learning rate: 1.417E-04 | global batch size: 256 | lm loss: 3.000817E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.573 | TFLOPs: 7.89 | +31: iteration 14620/ 37905 | consumed samples: 3742720 | consumed tokens: 7665090560 | elapsed time per iteration (s): 0.25 | learning rate: 1.416E-04 | global batch size: 256 | lm loss: 2.999964E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.978 | TFLOPs: 6.59 | +31: iteration 14630/ 37905 | consumed samples: 3745280 | consumed tokens: 7670333440 | elapsed time per iteration (s): 0.24 | learning rate: 1.416E-04 | global batch size: 256 | lm loss: 2.968987E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.705 | TFLOPs: 6.88 | +31: iteration 14640/ 37905 | consumed samples: 3747840 | consumed tokens: 7675576320 | elapsed time per iteration (s): 0.21 | learning rate: 1.415E-04 | global batch size: 256 | lm loss: 2.975729E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.583 | TFLOPs: 7.92 | +31: iteration 14650/ 37905 | consumed samples: 3750400 | consumed tokens: 7680819200 | elapsed time per iteration (s): 0.20 | learning rate: 1.414E-04 | global batch size: 256 | lm loss: 3.001281E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.619 | TFLOPs: 8.16 | +31: iteration 14660/ 37905 | consumed samples: 3752960 | consumed tokens: 7686062080 | elapsed time per iteration (s): 0.21 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 2.970919E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.374 | TFLOPs: 7.77 | +31: iteration 14670/ 37905 | consumed samples: 3755520 | consumed tokens: 7691304960 | elapsed time per iteration (s): 0.24 | learning rate: 1.413E-04 | global batch size: 256 | lm loss: 2.976505E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.904 | TFLOPs: 6.90 | +31: iteration 14680/ 37905 | consumed samples: 3758080 | consumed tokens: 7696547840 | elapsed time per iteration (s): 0.22 | learning rate: 1.412E-04 | global batch size: 256 | lm loss: 3.009334E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.546 | TFLOPs: 7.45 | +31: iteration 14690/ 37905 | consumed samples: 3760640 | consumed tokens: 7701790720 | elapsed time per iteration (s): 0.20 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 2.971589E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.933 | TFLOPs: 8.01 | +31: iteration 14700/ 37905 | consumed samples: 3763200 | consumed tokens: 7707033600 | elapsed time per iteration (s): 0.27 | learning rate: 1.411E-04 | global batch size: 256 | lm loss: 3.012048E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 953.276 | TFLOPs: 6.07 | +31: iteration 14710/ 37905 | consumed samples: 3765760 | consumed tokens: 7712276480 | elapsed time per iteration (s): 0.23 | learning rate: 1.410E-04 | global batch size: 256 | lm loss: 2.973268E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.736 | TFLOPs: 7.11 | +31: iteration 14720/ 37905 | consumed samples: 3768320 | consumed tokens: 7717519360 | elapsed time per iteration (s): 0.24 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 2.993949E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.539 | TFLOPs: 6.69 | +31: iteration 14730/ 37905 | consumed samples: 3770880 | consumed tokens: 7722762240 | elapsed time per iteration (s): 0.24 | learning rate: 1.409E-04 | global batch size: 256 | lm loss: 2.994545E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.919 | TFLOPs: 6.87 | +31: iteration 14740/ 37905 | consumed samples: 3773440 | consumed tokens: 7728005120 | elapsed time per iteration (s): 0.22 | learning rate: 1.408E-04 | global batch size: 256 | lm loss: 2.995120E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.583 | TFLOPs: 7.25 | +31: iteration 14750/ 37905 | consumed samples: 3776000 | consumed tokens: 7733248000 | elapsed time per iteration (s): 0.22 | learning rate: 1.407E-04 | global batch size: 256 | lm loss: 2.994319E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.115 | TFLOPs: 7.39 | +31: iteration 14760/ 37905 | consumed samples: 3778560 | consumed tokens: 7738490880 | elapsed time per iteration (s): 0.20 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 2.970424E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.885 | TFLOPs: 8.09 | +31: iteration 14770/ 37905 | consumed samples: 3781120 | consumed tokens: 7743733760 | elapsed time per iteration (s): 0.24 | learning rate: 1.406E-04 | global batch size: 256 | lm loss: 2.977776E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.206 | TFLOPs: 6.87 | +31: iteration 14780/ 37905 | consumed samples: 3783680 | consumed tokens: 7748976640 | elapsed time per iteration (s): 0.22 | learning rate: 1.405E-04 | global batch size: 256 | lm loss: 3.017186E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.540 | TFLOPs: 7.34 | +31: iteration 14790/ 37905 | consumed samples: 3786240 | consumed tokens: 7754219520 | elapsed time per iteration (s): 0.21 | learning rate: 1.404E-04 | global batch size: 256 | lm loss: 3.005318E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.736 | TFLOPs: 7.90 | +31: iteration 14800/ 37905 | consumed samples: 3788800 | consumed tokens: 7759462400 | elapsed time per iteration (s): 0.21 | learning rate: 1.404E-04 | global batch size: 256 | lm loss: 2.975598E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1208.479 | TFLOPs: 7.70 | +31: iteration 14810/ 37905 | consumed samples: 3791360 | consumed tokens: 7764705280 | elapsed time per iteration (s): 0.23 | learning rate: 1.403E-04 | global batch size: 256 | lm loss: 3.025483E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.720 | TFLOPs: 7.11 | +31: iteration 14820/ 37905 | consumed samples: 3793920 | consumed tokens: 7769948160 | elapsed time per iteration (s): 0.25 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 2.959996E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1015.731 | TFLOPs: 6.47 | +31: iteration 14830/ 37905 | consumed samples: 3796480 | consumed tokens: 7775191040 | elapsed time per iteration (s): 0.20 | learning rate: 1.402E-04 | global batch size: 256 | lm loss: 2.993781E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.721 | TFLOPs: 8.12 | +31: iteration 14840/ 37905 | consumed samples: 3799040 | consumed tokens: 7780433920 | elapsed time per iteration (s): 0.21 | learning rate: 1.401E-04 | global batch size: 256 | lm loss: 2.971744E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.998 | TFLOPs: 7.73 | +31: iteration 14850/ 37905 | consumed samples: 3801600 | consumed tokens: 7785676800 | elapsed time per iteration (s): 0.24 | learning rate: 1.400E-04 | global batch size: 256 | lm loss: 2.977475E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.907 | TFLOPs: 6.65 | +31: iteration 14860/ 37905 | consumed samples: 3804160 | consumed tokens: 7790919680 | elapsed time per iteration (s): 0.25 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 2.964722E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.956 | TFLOPs: 6.59 | +31: iteration 14870/ 37905 | consumed samples: 3806720 | consumed tokens: 7796162560 | elapsed time per iteration (s): 0.23 | learning rate: 1.399E-04 | global batch size: 256 | lm loss: 3.009869E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.297 | TFLOPs: 7.01 | +31: iteration 14880/ 37905 | consumed samples: 3809280 | consumed tokens: 7801405440 | elapsed time per iteration (s): 0.23 | learning rate: 1.398E-04 | global batch size: 256 | lm loss: 2.980484E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.603 | TFLOPs: 7.11 | +31: iteration 14890/ 37905 | consumed samples: 3811840 | consumed tokens: 7806648320 | elapsed time per iteration (s): 0.22 | learning rate: 1.397E-04 | global batch size: 256 | lm loss: 2.958713E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.959 | TFLOPs: 7.54 | +31: iteration 14900/ 37905 | consumed samples: 3814400 | consumed tokens: 7811891200 | elapsed time per iteration (s): 0.26 | learning rate: 1.397E-04 | global batch size: 256 | lm loss: 2.960368E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 995.693 | TFLOPs: 6.34 | +31: iteration 14910/ 37905 | consumed samples: 3816960 | consumed tokens: 7817134080 | elapsed time per iteration (s): 0.26 | learning rate: 1.396E-04 | global batch size: 256 | lm loss: 3.004717E+00 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 973.597 | TFLOPs: 6.20 | +31: iteration 14920/ 37905 | consumed samples: 3819520 | consumed tokens: 7822376960 | elapsed time per iteration (s): 0.21 | learning rate: 1.395E-04 | global batch size: 256 | lm loss: 2.962612E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.293 | TFLOPs: 7.83 | +31: iteration 14930/ 37905 | consumed samples: 3822080 | consumed tokens: 7827619840 | elapsed time per iteration (s): 0.25 | learning rate: 1.395E-04 | global batch size: 256 | lm loss: 2.969018E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.814 | TFLOPs: 6.58 | +31: iteration 14940/ 37905 | consumed samples: 3824640 | consumed tokens: 7832862720 | elapsed time per iteration (s): 0.24 | learning rate: 1.394E-04 | global batch size: 256 | lm loss: 2.993800E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.486 | TFLOPs: 6.93 | +31: iteration 14950/ 37905 | consumed samples: 3827200 | consumed tokens: 7838105600 | elapsed time per iteration (s): 0.23 | learning rate: 1.393E-04 | global batch size: 256 | lm loss: 2.961362E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.438 | TFLOPs: 7.17 | +31: iteration 14960/ 37905 | consumed samples: 3829760 | consumed tokens: 7843348480 | elapsed time per iteration (s): 0.19 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 2.931728E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1329.667 | TFLOPs: 8.47 | +31: iteration 14970/ 37905 | consumed samples: 3832320 | consumed tokens: 7848591360 | elapsed time per iteration (s): 0.24 | learning rate: 1.392E-04 | global batch size: 256 | lm loss: 2.973631E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.375 | TFLOPs: 6.89 | +31: iteration 14980/ 37905 | consumed samples: 3834880 | consumed tokens: 7853834240 | elapsed time per iteration (s): 0.23 | learning rate: 1.391E-04 | global batch size: 256 | lm loss: 2.984626E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.124 | TFLOPs: 7.19 | +31: iteration 14990/ 37905 | consumed samples: 3837440 | consumed tokens: 7859077120 | elapsed time per iteration (s): 0.21 | learning rate: 1.390E-04 | global batch size: 256 | lm loss: 3.039637E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.965 | TFLOPs: 7.76 | +31: iteration 15000/ 37905 | consumed samples: 3840000 | consumed tokens: 7864320000 | elapsed time per iteration (s): 0.21 | learning rate: 1.390E-04 | global batch size: 256 | lm loss: 2.972941E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.298 | TFLOPs: 7.80 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 15000 | lm loss value: 2.939229E+00 | lm loss PPL: 1.890126E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 15000 to checkpoints_83m + 0: [2022-11-24 15:04:32,472] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step15000 is begin to save! + 0: [2022-11-24 15:04:32,480] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,575] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,597] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,630] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,641] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,652] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,662] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:04:32,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:04:32,664] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step15000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:04:32,664] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:04:32,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:04:32,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:04:32,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:04:32,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:04:32,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:04:32,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +22: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:04:32,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +19: [2022-11-24 15:04:32,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:04:32,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +25: [2022-11-24 15:04:32,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:04:32,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:04:32,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:04:32,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:04:32,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:04:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +30: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +17: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +19: [2022-11-24 15:04:32,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +22: [2022-11-24 15:04:32,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:04:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 2: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +12: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +18: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:04:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +23: [2022-11-24 15:04:32,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +24: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +14: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +31: [2022-11-24 15:04:32,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 5: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 5: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +27: [2022-11-24 15:04:32,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:04:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:04:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +30: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +30: [2022-11-24 15:04:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +30: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:04:32,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +17: [2022-11-24 15:04:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:04:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:04:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +22: [2022-11-24 15:04:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:04:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:04:32,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:04:32,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +18: [2022-11-24 15:04:32,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 2: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +23: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +23: [2022-11-24 15:04:32,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +14: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +24: [2022-11-24 15:04:32,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:04:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +30: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +17: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:04:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:04:32,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:04:32,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +30: [2022-11-24 15:04:32,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:04:32,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +22: [2022-11-24 15:04:32,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +19: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:04:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +18: [2022-11-24 15:04:32,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:04:32,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 5: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +31: [2022-11-24 15:04:32,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +24: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:04:32,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:04:32,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:04:32,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:04:32,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:04:32,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:04:32,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +17: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +22: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:04:32,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:04:32,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +18: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:04:32,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:04:32,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 2: [2022-11-24 15:04:32,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 5: [2022-11-24 15:04:32,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +23: [2022-11-24 15:04:32,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +24: [2022-11-24 15:04:32,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +14: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +27: [2022-11-24 15:04:32,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:04:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:04:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:04:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +17: [2022-11-24 15:04:32,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:04:32,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +22: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:04:32,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +19: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:04:32,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:04:32,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +18: [2022-11-24 15:04:32,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 2: [2022-11-24 15:04:32,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +12: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:04:32,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +23: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 5: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:04:32,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:04:32,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +14: [2022-11-24 15:04:32,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +27: [2022-11-24 15:04:32,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +14: [2022-11-24 15:04:32,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:04:32,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +30: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:04:32,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:04:32,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:04:32,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +22: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +17: [2022-11-24 15:04:32,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:04:32,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +19: [2022-11-24 15:04:32,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:04:32,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:04:32,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:04:32,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +13: [2022-11-24 15:04:32,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +18: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +18: [2022-11-24 15:04:32,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 2: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +23: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:04:32,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 5: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:04:32,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +20: [2022-11-24 15:04:32,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +24: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +30: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +22: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +17: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +14: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +24: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +18: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +26: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +17: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +11: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 3: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +13: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +20: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +26: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +23: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +11: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +27: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +16: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +14: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 8: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +24: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +11: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +31: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +30: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +16: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +19: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:04:32,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +15: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +21: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +23: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +12: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +29: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 5: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +19: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 1: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 2: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +14: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +21: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 7: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 9: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +29: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:04:32,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +27: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 2: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 6: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 4: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +28: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +12: [2022-11-24 15:04:32,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +28: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +12: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +25: [2022-11-24 15:04:32,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:04:32,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:04:32,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! +10: [2022-11-24 15:04:32,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:04:32,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step15000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:04:32,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step15000 is ready now! + 0: successfully saved checkpoint at iteration 15000 to checkpoints_83m +31: time (ms) | save-checkpoint: 314.58 +31: iteration 15010/ 37905 | consumed samples: 3842560 | consumed tokens: 7869562880 | elapsed time per iteration (s): 0.25 | learning rate: 1.389E-04 | global batch size: 256 | lm loss: 2.991615E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.075 | TFLOPs: 6.57 | +31: iteration 15020/ 37905 | consumed samples: 3845120 | consumed tokens: 7874805760 | elapsed time per iteration (s): 0.22 | learning rate: 1.388E-04 | global batch size: 256 | lm loss: 2.970348E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.053 | TFLOPs: 7.31 | +31: iteration 15030/ 37905 | consumed samples: 3847680 | consumed tokens: 7880048640 | elapsed time per iteration (s): 0.21 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 3.001487E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.831 | TFLOPs: 7.72 | +31: iteration 15040/ 37905 | consumed samples: 3850240 | consumed tokens: 7885291520 | elapsed time per iteration (s): 0.22 | learning rate: 1.387E-04 | global batch size: 256 | lm loss: 3.033114E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.968 | TFLOPs: 7.27 | +31: iteration 15050/ 37905 | consumed samples: 3852800 | consumed tokens: 7890534400 | elapsed time per iteration (s): 0.24 | learning rate: 1.386E-04 | global batch size: 256 | lm loss: 2.966260E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.597 | TFLOPs: 6.86 | +31: iteration 15060/ 37905 | consumed samples: 3855360 | consumed tokens: 7895777280 | elapsed time per iteration (s): 0.23 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 2.966451E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.921 | TFLOPs: 7.01 | +31: iteration 15070/ 37905 | consumed samples: 3857920 | consumed tokens: 7901020160 | elapsed time per iteration (s): 0.21 | learning rate: 1.385E-04 | global batch size: 256 | lm loss: 2.977787E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.274 | TFLOPs: 7.85 | +31: iteration 15080/ 37905 | consumed samples: 3860480 | consumed tokens: 7906263040 | elapsed time per iteration (s): 0.21 | learning rate: 1.384E-04 | global batch size: 256 | lm loss: 2.966751E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.401 | TFLOPs: 7.92 | +31: iteration 15090/ 37905 | consumed samples: 3863040 | consumed tokens: 7911505920 | elapsed time per iteration (s): 0.23 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 2.972423E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.078 | TFLOPs: 7.13 | +31: iteration 15100/ 37905 | consumed samples: 3865600 | consumed tokens: 7916748800 | elapsed time per iteration (s): 0.23 | learning rate: 1.383E-04 | global batch size: 256 | lm loss: 2.961838E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.201 | TFLOPs: 6.94 | +31: iteration 15110/ 37905 | consumed samples: 3868160 | consumed tokens: 7921991680 | elapsed time per iteration (s): 0.22 | learning rate: 1.382E-04 | global batch size: 256 | lm loss: 2.997883E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.434 | TFLOPs: 7.35 | +31: iteration 15120/ 37905 | consumed samples: 3870720 | consumed tokens: 7927234560 | elapsed time per iteration (s): 0.22 | learning rate: 1.381E-04 | global batch size: 256 | lm loss: 2.980151E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.657 | TFLOPs: 7.37 | +31: iteration 15130/ 37905 | consumed samples: 3873280 | consumed tokens: 7932477440 | elapsed time per iteration (s): 0.21 | learning rate: 1.380E-04 | global batch size: 256 | lm loss: 2.960398E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.242 | TFLOPs: 7.70 | +31: iteration 15140/ 37905 | consumed samples: 3875840 | consumed tokens: 7937720320 | elapsed time per iteration (s): 0.24 | learning rate: 1.380E-04 | global batch size: 256 | lm loss: 3.010171E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.448 | TFLOPs: 6.84 | +31: iteration 15150/ 37905 | consumed samples: 3878400 | consumed tokens: 7942963200 | elapsed time per iteration (s): 0.21 | learning rate: 1.379E-04 | global batch size: 256 | lm loss: 2.959819E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.117 | TFLOPs: 7.90 | +31: iteration 15160/ 37905 | consumed samples: 3880960 | consumed tokens: 7948206080 | elapsed time per iteration (s): 0.25 | learning rate: 1.378E-04 | global batch size: 256 | lm loss: 2.975990E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.318 | TFLOPs: 6.65 | +31: iteration 15170/ 37905 | consumed samples: 3883520 | consumed tokens: 7953448960 | elapsed time per iteration (s): 0.23 | learning rate: 1.378E-04 | global batch size: 256 | lm loss: 3.000325E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.262 | TFLOPs: 7.10 | +31: iteration 15180/ 37905 | consumed samples: 3886080 | consumed tokens: 7958691840 | elapsed time per iteration (s): 0.21 | learning rate: 1.377E-04 | global batch size: 256 | lm loss: 2.966615E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.036 | TFLOPs: 7.90 | +31: iteration 15190/ 37905 | consumed samples: 3888640 | consumed tokens: 7963934720 | elapsed time per iteration (s): 0.21 | learning rate: 1.376E-04 | global batch size: 256 | lm loss: 2.974675E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.777 | TFLOPs: 7.68 | +31: iteration 15200/ 37905 | consumed samples: 3891200 | consumed tokens: 7969177600 | elapsed time per iteration (s): 0.26 | learning rate: 1.375E-04 | global batch size: 256 | lm loss: 3.002310E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 995.389 | TFLOPs: 6.34 | +31: iteration 15210/ 37905 | consumed samples: 3893760 | consumed tokens: 7974420480 | elapsed time per iteration (s): 0.27 | learning rate: 1.375E-04 | global batch size: 256 | lm loss: 2.976815E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 945.849 | TFLOPs: 6.02 | +31: iteration 15220/ 37905 | consumed samples: 3896320 | consumed tokens: 7979663360 | elapsed time per iteration (s): 0.27 | learning rate: 1.374E-04 | global batch size: 256 | lm loss: 3.004286E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 938.595 | TFLOPs: 5.98 | +31: iteration 15230/ 37905 | consumed samples: 3898880 | consumed tokens: 7984906240 | elapsed time per iteration (s): 0.25 | learning rate: 1.373E-04 | global batch size: 256 | lm loss: 2.984645E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.572 | TFLOPs: 6.42 | +31: iteration 15240/ 37905 | consumed samples: 3901440 | consumed tokens: 7990149120 | elapsed time per iteration (s): 0.21 | learning rate: 1.373E-04 | global batch size: 256 | lm loss: 2.987711E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.787 | TFLOPs: 7.64 | +31: iteration 15250/ 37905 | consumed samples: 3904000 | consumed tokens: 7995392000 | elapsed time per iteration (s): 0.21 | learning rate: 1.372E-04 | global batch size: 256 | lm loss: 2.974136E+00 | grad norm: 0.273 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.036 | TFLOPs: 7.77 | +31: iteration 15260/ 37905 | consumed samples: 3906560 | consumed tokens: 8000634880 | elapsed time per iteration (s): 0.21 | learning rate: 1.371E-04 | global batch size: 256 | lm loss: 3.004832E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.819 | TFLOPs: 7.77 | +31: iteration 15270/ 37905 | consumed samples: 3909120 | consumed tokens: 8005877760 | elapsed time per iteration (s): 0.25 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 2.973833E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.867 | TFLOPs: 6.49 | +31: iteration 15280/ 37905 | consumed samples: 3911680 | consumed tokens: 8011120640 | elapsed time per iteration (s): 0.24 | learning rate: 1.370E-04 | global batch size: 256 | lm loss: 2.991570E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.365 | TFLOPs: 6.76 | +31: iteration 15290/ 37905 | consumed samples: 3914240 | consumed tokens: 8016363520 | elapsed time per iteration (s): 0.21 | learning rate: 1.369E-04 | global batch size: 256 | lm loss: 2.968252E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1208.353 | TFLOPs: 7.70 | +31: iteration 15300/ 37905 | consumed samples: 3916800 | consumed tokens: 8021606400 | elapsed time per iteration (s): 0.25 | learning rate: 1.368E-04 | global batch size: 256 | lm loss: 2.968732E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.035 | TFLOPs: 6.53 | +31: iteration 15310/ 37905 | consumed samples: 3919360 | consumed tokens: 8026849280 | elapsed time per iteration (s): 0.23 | learning rate: 1.368E-04 | global batch size: 256 | lm loss: 2.993764E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.477 | TFLOPs: 7.06 | +31: iteration 15320/ 37905 | consumed samples: 3921920 | consumed tokens: 8032092160 | elapsed time per iteration (s): 0.20 | learning rate: 1.367E-04 | global batch size: 256 | lm loss: 2.979026E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1276.368 | TFLOPs: 8.13 | +31: iteration 15330/ 37905 | consumed samples: 3924480 | consumed tokens: 8037335040 | elapsed time per iteration (s): 0.27 | learning rate: 1.366E-04 | global batch size: 256 | lm loss: 2.959890E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 946.059 | TFLOPs: 6.03 | +31: iteration 15340/ 37905 | consumed samples: 3927040 | consumed tokens: 8042577920 | elapsed time per iteration (s): 0.28 | learning rate: 1.365E-04 | global batch size: 256 | lm loss: 2.995689E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 917.076 | TFLOPs: 5.84 | +31: iteration 15350/ 37905 | consumed samples: 3929600 | consumed tokens: 8047820800 | elapsed time per iteration (s): 0.22 | learning rate: 1.365E-04 | global batch size: 256 | lm loss: 2.981910E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.230 | TFLOPs: 7.41 | +31: iteration 15360/ 37905 | consumed samples: 3932160 | consumed tokens: 8053063680 | elapsed time per iteration (s): 0.22 | learning rate: 1.364E-04 | global batch size: 256 | lm loss: 2.984954E+00 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.938 | TFLOPs: 7.32 | +31: iteration 15370/ 37905 | consumed samples: 3934720 | consumed tokens: 8058306560 | elapsed time per iteration (s): 0.23 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 2.994675E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.261 | TFLOPs: 7.05 | +31: iteration 15380/ 37905 | consumed samples: 3937280 | consumed tokens: 8063549440 | elapsed time per iteration (s): 0.23 | learning rate: 1.363E-04 | global batch size: 256 | lm loss: 2.951441E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.355 | TFLOPs: 7.04 | +31: iteration 15390/ 37905 | consumed samples: 3939840 | consumed tokens: 8068792320 | elapsed time per iteration (s): 0.21 | learning rate: 1.362E-04 | global batch size: 256 | lm loss: 2.999288E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.881 | TFLOPs: 7.60 | +31: iteration 15400/ 37905 | consumed samples: 3942400 | consumed tokens: 8074035200 | elapsed time per iteration (s): 0.22 | learning rate: 1.361E-04 | global batch size: 256 | lm loss: 2.967600E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.448 | TFLOPs: 7.25 | +31: iteration 15410/ 37905 | consumed samples: 3944960 | consumed tokens: 8079278080 | elapsed time per iteration (s): 0.20 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 3.018240E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.903 | TFLOPs: 8.25 | +31: iteration 15420/ 37905 | consumed samples: 3947520 | consumed tokens: 8084520960 | elapsed time per iteration (s): 0.23 | learning rate: 1.360E-04 | global batch size: 256 | lm loss: 3.001823E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.747 | TFLOPs: 7.03 | +31: iteration 15430/ 37905 | consumed samples: 3950080 | consumed tokens: 8089763840 | elapsed time per iteration (s): 0.22 | learning rate: 1.359E-04 | global batch size: 256 | lm loss: 2.974277E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.387 | TFLOPs: 7.29 | +31: iteration 15440/ 37905 | consumed samples: 3952640 | consumed tokens: 8095006720 | elapsed time per iteration (s): 0.23 | learning rate: 1.358E-04 | global batch size: 256 | lm loss: 2.971915E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.173 | TFLOPs: 7.13 | +31: iteration 15450/ 37905 | consumed samples: 3955200 | consumed tokens: 8100249600 | elapsed time per iteration (s): 0.22 | learning rate: 1.358E-04 | global batch size: 256 | lm loss: 2.989213E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.961 | TFLOPs: 7.49 | +31: iteration 15460/ 37905 | consumed samples: 3957760 | consumed tokens: 8105492480 | elapsed time per iteration (s): 0.22 | learning rate: 1.357E-04 | global batch size: 256 | lm loss: 2.988458E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.211 | TFLOPs: 7.38 | +31: iteration 15470/ 37905 | consumed samples: 3960320 | consumed tokens: 8110735360 | elapsed time per iteration (s): 0.22 | learning rate: 1.356E-04 | global batch size: 256 | lm loss: 2.986896E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.066 | TFLOPs: 7.53 | +31: iteration 15480/ 37905 | consumed samples: 3962880 | consumed tokens: 8115978240 | elapsed time per iteration (s): 0.21 | learning rate: 1.355E-04 | global batch size: 256 | lm loss: 2.991458E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.984 | TFLOPs: 7.73 | +31: iteration 15490/ 37905 | consumed samples: 3965440 | consumed tokens: 8121221120 | elapsed time per iteration (s): 0.21 | learning rate: 1.355E-04 | global batch size: 256 | lm loss: 2.981701E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1198.658 | TFLOPs: 7.63 | +31: iteration 15500/ 37905 | consumed samples: 3968000 | consumed tokens: 8126464000 | elapsed time per iteration (s): 0.21 | learning rate: 1.354E-04 | global batch size: 256 | lm loss: 2.984310E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.902 | TFLOPs: 7.79 | +31: iteration 15510/ 37905 | consumed samples: 3970560 | consumed tokens: 8131706880 | elapsed time per iteration (s): 0.22 | learning rate: 1.353E-04 | global batch size: 256 | lm loss: 2.995220E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.442 | TFLOPs: 7.50 | +31: iteration 15520/ 37905 | consumed samples: 3973120 | consumed tokens: 8136949760 | elapsed time per iteration (s): 0.21 | learning rate: 1.353E-04 | global batch size: 256 | lm loss: 2.983123E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.046 | TFLOPs: 7.85 | +31: iteration 15530/ 37905 | consumed samples: 3975680 | consumed tokens: 8142192640 | elapsed time per iteration (s): 0.22 | learning rate: 1.352E-04 | global batch size: 256 | lm loss: 3.008068E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.132 | TFLOPs: 7.56 | +31: iteration 15540/ 37905 | consumed samples: 3978240 | consumed tokens: 8147435520 | elapsed time per iteration (s): 0.22 | learning rate: 1.351E-04 | global batch size: 256 | lm loss: 3.000628E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.349 | TFLOPs: 7.55 | +31: iteration 15550/ 37905 | consumed samples: 3980800 | consumed tokens: 8152678400 | elapsed time per iteration (s): 0.23 | learning rate: 1.350E-04 | global batch size: 256 | lm loss: 2.955636E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.886 | TFLOPs: 7.13 | +31: iteration 15560/ 37905 | consumed samples: 3983360 | consumed tokens: 8157921280 | elapsed time per iteration (s): 0.23 | learning rate: 1.350E-04 | global batch size: 256 | lm loss: 2.984892E+00 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.465 | TFLOPs: 7.10 | +31: iteration 15570/ 37905 | consumed samples: 3985920 | consumed tokens: 8163164160 | elapsed time per iteration (s): 0.21 | learning rate: 1.349E-04 | global batch size: 256 | lm loss: 2.968909E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.174 | TFLOPs: 7.80 | +31: iteration 15580/ 37905 | consumed samples: 3988480 | consumed tokens: 8168407040 | elapsed time per iteration (s): 0.24 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 2.973738E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.154 | TFLOPs: 6.90 | +31: iteration 15590/ 37905 | consumed samples: 3991040 | consumed tokens: 8173649920 | elapsed time per iteration (s): 0.22 | learning rate: 1.348E-04 | global batch size: 256 | lm loss: 3.006439E+00 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.941 | TFLOPs: 7.27 | +31: iteration 15600/ 37905 | consumed samples: 3993600 | consumed tokens: 8178892800 | elapsed time per iteration (s): 0.22 | learning rate: 1.347E-04 | global batch size: 256 | lm loss: 2.978842E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.539 | TFLOPs: 7.33 | +31: iteration 15610/ 37905 | consumed samples: 3996160 | consumed tokens: 8184135680 | elapsed time per iteration (s): 0.24 | learning rate: 1.346E-04 | global batch size: 256 | lm loss: 3.000751E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.159 | TFLOPs: 6.89 | +31: iteration 15620/ 37905 | consumed samples: 3998720 | consumed tokens: 8189378560 | elapsed time per iteration (s): 0.22 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 2.958916E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.172 | TFLOPs: 7.55 | +31: iteration 15630/ 37905 | consumed samples: 4001280 | consumed tokens: 8194621440 | elapsed time per iteration (s): 0.24 | learning rate: 1.345E-04 | global batch size: 256 | lm loss: 2.999078E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.998 | TFLOPs: 6.72 | +31: iteration 15640/ 37905 | consumed samples: 4003840 | consumed tokens: 8199864320 | elapsed time per iteration (s): 0.24 | learning rate: 1.344E-04 | global batch size: 256 | lm loss: 2.985185E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.613 | TFLOPs: 6.85 | +31: iteration 15650/ 37905 | consumed samples: 4006400 | consumed tokens: 8205107200 | elapsed time per iteration (s): 0.22 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 3.020443E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.158 | TFLOPs: 7.38 | +31: iteration 15660/ 37905 | consumed samples: 4008960 | consumed tokens: 8210350080 | elapsed time per iteration (s): 0.23 | learning rate: 1.343E-04 | global batch size: 256 | lm loss: 2.948475E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.892 | TFLOPs: 7.08 | +31: iteration 15670/ 37905 | consumed samples: 4011520 | consumed tokens: 8215592960 | elapsed time per iteration (s): 0.23 | learning rate: 1.342E-04 | global batch size: 256 | lm loss: 2.982059E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.142 | TFLOPs: 7.13 | +31: iteration 15680/ 37905 | consumed samples: 4014080 | consumed tokens: 8220835840 | elapsed time per iteration (s): 0.25 | learning rate: 1.341E-04 | global batch size: 256 | lm loss: 2.967236E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.449 | TFLOPs: 6.59 | +31: iteration 15690/ 37905 | consumed samples: 4016640 | consumed tokens: 8226078720 | elapsed time per iteration (s): 0.20 | learning rate: 1.340E-04 | global batch size: 256 | lm loss: 3.009695E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1301.800 | TFLOPs: 8.29 | +31: iteration 15700/ 37905 | consumed samples: 4019200 | consumed tokens: 8231321600 | elapsed time per iteration (s): 0.24 | learning rate: 1.340E-04 | global batch size: 256 | lm loss: 2.988397E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.896 | TFLOPs: 6.92 | +31: iteration 15710/ 37905 | consumed samples: 4021760 | consumed tokens: 8236564480 | elapsed time per iteration (s): 0.20 | learning rate: 1.339E-04 | global batch size: 256 | lm loss: 3.007179E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.209 | TFLOPs: 8.15 | +31: iteration 15720/ 37905 | consumed samples: 4024320 | consumed tokens: 8241807360 | elapsed time per iteration (s): 0.19 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 3.012388E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.588 | TFLOPs: 8.56 | +31: iteration 15730/ 37905 | consumed samples: 4026880 | consumed tokens: 8247050240 | elapsed time per iteration (s): 0.23 | learning rate: 1.338E-04 | global batch size: 256 | lm loss: 2.994529E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.953 | TFLOPs: 7.22 | +31: iteration 15740/ 37905 | consumed samples: 4029440 | consumed tokens: 8252293120 | elapsed time per iteration (s): 0.20 | learning rate: 1.337E-04 | global batch size: 256 | lm loss: 2.986327E+00 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1292.794 | TFLOPs: 8.23 | +31: iteration 15750/ 37905 | consumed samples: 4032000 | consumed tokens: 8257536000 | elapsed time per iteration (s): 0.19 | learning rate: 1.336E-04 | global batch size: 256 | lm loss: 2.978075E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1372.305 | TFLOPs: 8.74 | +31: iteration 15760/ 37905 | consumed samples: 4034560 | consumed tokens: 8262778880 | elapsed time per iteration (s): 0.22 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 2.989008E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.382 | TFLOPs: 7.56 | +31: iteration 15770/ 37905 | consumed samples: 4037120 | consumed tokens: 8268021760 | elapsed time per iteration (s): 0.22 | learning rate: 1.335E-04 | global batch size: 256 | lm loss: 2.991324E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.946 | TFLOPs: 7.43 | +31: iteration 15780/ 37905 | consumed samples: 4039680 | consumed tokens: 8273264640 | elapsed time per iteration (s): 0.20 | learning rate: 1.334E-04 | global batch size: 256 | lm loss: 2.967592E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.173 | TFLOPs: 8.12 | +31: iteration 15790/ 37905 | consumed samples: 4042240 | consumed tokens: 8278507520 | elapsed time per iteration (s): 0.21 | learning rate: 1.333E-04 | global batch size: 256 | lm loss: 2.961855E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.708 | TFLOPs: 7.72 | +31: iteration 15800/ 37905 | consumed samples: 4044800 | consumed tokens: 8283750400 | elapsed time per iteration (s): 0.21 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 2.959839E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.964 | TFLOPs: 7.90 | +31: iteration 15810/ 37905 | consumed samples: 4047360 | consumed tokens: 8288993280 | elapsed time per iteration (s): 0.21 | learning rate: 1.332E-04 | global batch size: 256 | lm loss: 2.941486E+00 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.554 | TFLOPs: 7.67 | +31: iteration 15820/ 37905 | consumed samples: 4049920 | consumed tokens: 8294236160 | elapsed time per iteration (s): 0.20 | learning rate: 1.331E-04 | global batch size: 256 | lm loss: 3.012320E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.933 | TFLOPs: 8.09 | +31: iteration 15830/ 37905 | consumed samples: 4052480 | consumed tokens: 8299479040 | elapsed time per iteration (s): 0.21 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 2.988045E+00 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.126 | TFLOPs: 7.61 | +31: iteration 15840/ 37905 | consumed samples: 4055040 | consumed tokens: 8304721920 | elapsed time per iteration (s): 0.20 | learning rate: 1.330E-04 | global batch size: 256 | lm loss: 2.994741E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.176 | TFLOPs: 7.96 | +31: iteration 15850/ 37905 | consumed samples: 4057600 | consumed tokens: 8309964800 | elapsed time per iteration (s): 0.25 | learning rate: 1.329E-04 | global batch size: 256 | lm loss: 2.993406E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1010.723 | TFLOPs: 6.44 | +31: iteration 15860/ 37905 | consumed samples: 4060160 | consumed tokens: 8315207680 | elapsed time per iteration (s): 0.23 | learning rate: 1.328E-04 | global batch size: 256 | lm loss: 2.971733E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.126 | TFLOPs: 7.06 | +31: iteration 15870/ 37905 | consumed samples: 4062720 | consumed tokens: 8320450560 | elapsed time per iteration (s): 0.26 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 2.965896E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 974.816 | TFLOPs: 6.21 | +31: iteration 15880/ 37905 | consumed samples: 4065280 | consumed tokens: 8325693440 | elapsed time per iteration (s): 0.21 | learning rate: 1.327E-04 | global batch size: 256 | lm loss: 2.966913E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.419 | TFLOPs: 7.73 | +31: iteration 15890/ 37905 | consumed samples: 4067840 | consumed tokens: 8330936320 | elapsed time per iteration (s): 0.21 | learning rate: 1.326E-04 | global batch size: 256 | lm loss: 2.983228E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.576 | TFLOPs: 7.77 | +31: iteration 15900/ 37905 | consumed samples: 4070400 | consumed tokens: 8336179200 | elapsed time per iteration (s): 0.24 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 2.990758E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.968 | TFLOPs: 6.80 | +31: iteration 15910/ 37905 | consumed samples: 4072960 | consumed tokens: 8341422080 | elapsed time per iteration (s): 0.24 | learning rate: 1.325E-04 | global batch size: 256 | lm loss: 2.992155E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.870 | TFLOPs: 6.79 | +31: iteration 15920/ 37905 | consumed samples: 4075520 | consumed tokens: 8346664960 | elapsed time per iteration (s): 0.23 | learning rate: 1.324E-04 | global batch size: 256 | lm loss: 2.937210E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.757 | TFLOPs: 7.12 | +31: iteration 15930/ 37905 | consumed samples: 4078080 | consumed tokens: 8351907840 | elapsed time per iteration (s): 0.21 | learning rate: 1.323E-04 | global batch size: 256 | lm loss: 2.967169E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.648 | TFLOPs: 7.62 | +31: iteration 15940/ 37905 | consumed samples: 4080640 | consumed tokens: 8357150720 | elapsed time per iteration (s): 0.21 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 2.976060E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.686 | TFLOPs: 7.93 | +31: iteration 15950/ 37905 | consumed samples: 4083200 | consumed tokens: 8362393600 | elapsed time per iteration (s): 0.23 | learning rate: 1.322E-04 | global batch size: 256 | lm loss: 2.993598E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.526 | TFLOPs: 7.17 | +31: iteration 15960/ 37905 | consumed samples: 4085760 | consumed tokens: 8367636480 | elapsed time per iteration (s): 0.23 | learning rate: 1.321E-04 | global batch size: 256 | lm loss: 2.961561E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.602 | TFLOPs: 7.22 | +31: iteration 15970/ 37905 | consumed samples: 4088320 | consumed tokens: 8372879360 | elapsed time per iteration (s): 0.21 | learning rate: 1.320E-04 | global batch size: 256 | lm loss: 2.983740E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.379 | TFLOPs: 7.75 | +31: iteration 15980/ 37905 | consumed samples: 4090880 | consumed tokens: 8378122240 | elapsed time per iteration (s): 0.21 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 3.006079E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.659 | TFLOPs: 7.61 | +31: iteration 15990/ 37905 | consumed samples: 4093440 | consumed tokens: 8383365120 | elapsed time per iteration (s): 0.22 | learning rate: 1.319E-04 | global batch size: 256 | lm loss: 2.993465E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.020 | TFLOPs: 7.41 | + 0: [2022-11-24 15:08:16,224] [INFO] [logging.py:68:log_dist] [Rank 0] step=16000, skipped=0, lr=[0.00013180458311343816, 0.00013180458311343816, 0.00013180458311343816], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 16000/ 37905 | consumed samples: 4096000 | consumed tokens: 8388608000 | elapsed time per iteration (s): 0.21 | learning rate: 1.318E-04 | global batch size: 256 | lm loss: 2.979698E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.086 | TFLOPs: 7.61 | + 0: steps: 16000 loss: 3.0961 iter time (s): 0.222 samples/sec: 1153.248 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 16000 | lm loss value: 2.804527E+00 | lm loss PPL: 1.651925E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 16000 to checkpoints_83m + 0: [2022-11-24 15:08:16,306] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step16000 is begin to save! + 0: [2022-11-24 15:08:16,316] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,399] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,411] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,422] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,443] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,454] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,498] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:08:16,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:08:16,499] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step16000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:08:16,499] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:08:16,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:08:16,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step16000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:08:16,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 15:08:16,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:08:16,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +11: [2022-11-24 15:08:16,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +20: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +13: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:08:16,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +16: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +13: [2022-11-24 15:08:16,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 9: [2022-11-24 15:08:16,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:08:16,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +22: [2022-11-24 15:08:16,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:08:16,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:08:16,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +30: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +29: [2022-11-24 15:08:16,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:08:16,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 6: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 2: [2022-11-24 15:08:16,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +23: [2022-11-24 15:08:16,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +26: [2022-11-24 15:08:16,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +11: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:08:16,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +18: [2022-11-24 15:08:16,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +20: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +20: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 9: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +13: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +13: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:08:16,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +16: [2022-11-24 15:08:16,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +16: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:08:16,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +22: [2022-11-24 15:08:16,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +22: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,605] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,606] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:08:16,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:08:16,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +30: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +30: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:08:16,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,607] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 6: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:08:16,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 6: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:08:16,608] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +23: [2022-11-24 15:08:16,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +12: [2022-11-24 15:08:16,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,609] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +11: [2022-11-24 15:08:16,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +18: [2022-11-24 15:08:16,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,610] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:08:16,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:08:16,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +20: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +13: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:08:16,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 9: [2022-11-24 15:08:16,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,611] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +22: [2022-11-24 15:08:16,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:08:16,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,612] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:08:16,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +16: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:08:16,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:08:16,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +30: [2022-11-24 15:08:16,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +30: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 2: [2022-11-24 15:08:16,613] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:08:16,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:08:16,614] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,614] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +26: [2022-11-24 15:08:16,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +29: [2022-11-24 15:08:16,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:08:16,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:08:16,615] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:08:16,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +23: [2022-11-24 15:08:16,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:08:16,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,616] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 15:08:16,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +11: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +18: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,617] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,617] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +20: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,618] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:08:16,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +13: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +13: [2022-11-24 15:08:16,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:08:16,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +22: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,619] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:08:16,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +16: [2022-11-24 15:08:16,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:08:16,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:08:16,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,620] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:08:16,620] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +30: [2022-11-24 15:08:16,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:08:16,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 2: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:08:16,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 6: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,621] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,621] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:08:16,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:08:16,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +29: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:08:16,622] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,622] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +23: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +26: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,623] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +26: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:08:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:08:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +11: [2022-11-24 15:08:16,624] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +18: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:08:16,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,625] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:08:16,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +20: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +13: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +22: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 9: [2022-11-24 15:08:16,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:08:16,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +16: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:08:16,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +30: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:08:16,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +30: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 2: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 6: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:08:16,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:08:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:08:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:08:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +29: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +29: [2022-11-24 15:08:16,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:08:16,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +23: [2022-11-24 15:08:16,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:08:16,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:08:16,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:08:16,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +11: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:08:16,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +18: [2022-11-24 15:08:16,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:08:16,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +20: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +13: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:08:16,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 9: [2022-11-24 15:08:16,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +22: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:08:16,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +16: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:08:16,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 7: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 6: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +30: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:08:16,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 2: [2022-11-24 15:08:16,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:08:16,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:08:16,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:08:16,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +26: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:08:16,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:08:16,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +23: [2022-11-24 15:08:16,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:08:16,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:08:16,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:08:16,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +18: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +11: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +21: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +13: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +12: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +24: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +24: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +12: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +10: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +30: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 2: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +21: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +18: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +11: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 9: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +10: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +29: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +28: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +22: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +20: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +23: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +22: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 2: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 3: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +20: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +26: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +23: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 9: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +25: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 6: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 8: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +29: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +28: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +25: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +14: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +26: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +15: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 5: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +19: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +14: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 4: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +26: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +17: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +19: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 1: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +15: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +17: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +31: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +16: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:08:16,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:08:16,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:08:16,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +16: [2022-11-24 15:08:16,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! +27: [2022-11-24 15:08:16,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:08:16,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step16000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:08:16,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step16000 is ready now! + 0: successfully saved checkpoint at iteration 16000 to checkpoints_83m +31: time (ms) | save-checkpoint: 339.07 +31: iteration 16010/ 37905 | consumed samples: 4098560 | consumed tokens: 8393850880 | elapsed time per iteration (s): 0.26 | learning rate: 1.317E-04 | global batch size: 256 | lm loss: 2.970881E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 994.959 | TFLOPs: 6.34 | +31: iteration 16020/ 37905 | consumed samples: 4101120 | consumed tokens: 8399093760 | elapsed time per iteration (s): 0.22 | learning rate: 1.317E-04 | global batch size: 256 | lm loss: 2.977033E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.493 | TFLOPs: 7.44 | +31: iteration 16030/ 37905 | consumed samples: 4103680 | consumed tokens: 8404336640 | elapsed time per iteration (s): 0.21 | learning rate: 1.316E-04 | global batch size: 256 | lm loss: 2.964324E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.514 | TFLOPs: 7.85 | +31: iteration 16040/ 37905 | consumed samples: 4106240 | consumed tokens: 8409579520 | elapsed time per iteration (s): 0.21 | learning rate: 1.315E-04 | global batch size: 256 | lm loss: 3.010786E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.266 | TFLOPs: 7.89 | +31: iteration 16050/ 37905 | consumed samples: 4108800 | consumed tokens: 8414822400 | elapsed time per iteration (s): 0.24 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 2.936229E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.006 | TFLOPs: 6.88 | +31: iteration 16060/ 37905 | consumed samples: 4111360 | consumed tokens: 8420065280 | elapsed time per iteration (s): 0.21 | learning rate: 1.314E-04 | global batch size: 256 | lm loss: 3.014559E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.172 | TFLOPs: 7.62 | +31: iteration 16070/ 37905 | consumed samples: 4113920 | consumed tokens: 8425308160 | elapsed time per iteration (s): 0.23 | learning rate: 1.313E-04 | global batch size: 256 | lm loss: 2.972627E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.087 | TFLOPs: 7.20 | +31: iteration 16080/ 37905 | consumed samples: 4116480 | consumed tokens: 8430551040 | elapsed time per iteration (s): 0.20 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 2.967296E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1298.598 | TFLOPs: 8.27 | +31: iteration 16090/ 37905 | consumed samples: 4119040 | consumed tokens: 8435793920 | elapsed time per iteration (s): 0.23 | learning rate: 1.312E-04 | global batch size: 256 | lm loss: 2.978832E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.047 | TFLOPs: 7.16 | +31: iteration 16100/ 37905 | consumed samples: 4121600 | consumed tokens: 8441036800 | elapsed time per iteration (s): 0.22 | learning rate: 1.311E-04 | global batch size: 256 | lm loss: 2.951102E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.885 | TFLOPs: 7.55 | +31: iteration 16110/ 37905 | consumed samples: 4124160 | consumed tokens: 8446279680 | elapsed time per iteration (s): 0.22 | learning rate: 1.310E-04 | global batch size: 256 | lm loss: 2.986599E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.360 | TFLOPs: 7.26 | +31: iteration 16120/ 37905 | consumed samples: 4126720 | consumed tokens: 8451522560 | elapsed time per iteration (s): 0.20 | learning rate: 1.309E-04 | global batch size: 256 | lm loss: 2.996516E+00 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1262.952 | TFLOPs: 8.04 | +31: iteration 16130/ 37905 | consumed samples: 4129280 | consumed tokens: 8456765440 | elapsed time per iteration (s): 0.22 | learning rate: 1.309E-04 | global batch size: 256 | lm loss: 2.967508E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.052 | TFLOPs: 7.53 | +31: iteration 16140/ 37905 | consumed samples: 4131840 | consumed tokens: 8462008320 | elapsed time per iteration (s): 0.21 | learning rate: 1.308E-04 | global batch size: 256 | lm loss: 2.947334E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.608 | TFLOPs: 7.81 | +31: iteration 16150/ 37905 | consumed samples: 4134400 | consumed tokens: 8467251200 | elapsed time per iteration (s): 0.22 | learning rate: 1.307E-04 | global batch size: 256 | lm loss: 2.979207E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.198 | TFLOPs: 7.36 | +31: iteration 16160/ 37905 | consumed samples: 4136960 | consumed tokens: 8472494080 | elapsed time per iteration (s): 0.21 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 2.972243E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.181 | TFLOPs: 7.67 | +31: iteration 16170/ 37905 | consumed samples: 4139520 | consumed tokens: 8477736960 | elapsed time per iteration (s): 0.23 | learning rate: 1.306E-04 | global batch size: 256 | lm loss: 2.960997E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.602 | TFLOPs: 7.21 | +31: iteration 16180/ 37905 | consumed samples: 4142080 | consumed tokens: 8482979840 | elapsed time per iteration (s): 0.22 | learning rate: 1.305E-04 | global batch size: 256 | lm loss: 2.992763E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.937 | TFLOPs: 7.36 | +31: iteration 16190/ 37905 | consumed samples: 4144640 | consumed tokens: 8488222720 | elapsed time per iteration (s): 0.23 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 2.948575E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.279 | TFLOPs: 7.12 | +31: iteration 16200/ 37905 | consumed samples: 4147200 | consumed tokens: 8493465600 | elapsed time per iteration (s): 0.23 | learning rate: 1.304E-04 | global batch size: 256 | lm loss: 2.971490E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.577 | TFLOPs: 7.17 | +31: iteration 16210/ 37905 | consumed samples: 4149760 | consumed tokens: 8498708480 | elapsed time per iteration (s): 0.23 | learning rate: 1.303E-04 | global batch size: 256 | lm loss: 2.968464E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.898 | TFLOPs: 6.97 | +31: iteration 16220/ 37905 | consumed samples: 4152320 | consumed tokens: 8503951360 | elapsed time per iteration (s): 0.25 | learning rate: 1.302E-04 | global batch size: 256 | lm loss: 2.955952E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.155 | TFLOPs: 6.56 | +31: iteration 16230/ 37905 | consumed samples: 4154880 | consumed tokens: 8509194240 | elapsed time per iteration (s): 0.23 | learning rate: 1.301E-04 | global batch size: 256 | lm loss: 2.965356E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.584 | TFLOPs: 7.15 | +31: iteration 16240/ 37905 | consumed samples: 4157440 | consumed tokens: 8514437120 | elapsed time per iteration (s): 0.28 | learning rate: 1.301E-04 | global batch size: 256 | lm loss: 2.957588E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 926.284 | TFLOPs: 5.90 | +31: iteration 16250/ 37905 | consumed samples: 4160000 | consumed tokens: 8519680000 | elapsed time per iteration (s): 0.21 | learning rate: 1.300E-04 | global batch size: 256 | lm loss: 2.988751E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.129 | TFLOPs: 7.64 | +31: iteration 16260/ 37905 | consumed samples: 4162560 | consumed tokens: 8524922880 | elapsed time per iteration (s): 0.22 | learning rate: 1.299E-04 | global batch size: 256 | lm loss: 2.960588E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.662 | TFLOPs: 7.56 | +31: iteration 16270/ 37905 | consumed samples: 4165120 | consumed tokens: 8530165760 | elapsed time per iteration (s): 0.21 | learning rate: 1.298E-04 | global batch size: 256 | lm loss: 2.948372E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.173 | TFLOPs: 7.75 | +31: iteration 16280/ 37905 | consumed samples: 4167680 | consumed tokens: 8535408640 | elapsed time per iteration (s): 0.20 | learning rate: 1.298E-04 | global batch size: 256 | lm loss: 2.968216E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.822 | TFLOPs: 8.06 | +31: iteration 16290/ 37905 | consumed samples: 4170240 | consumed tokens: 8540651520 | elapsed time per iteration (s): 0.20 | learning rate: 1.297E-04 | global batch size: 256 | lm loss: 2.984109E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.244 | TFLOPs: 7.96 | +31: iteration 16300/ 37905 | consumed samples: 4172800 | consumed tokens: 8545894400 | elapsed time per iteration (s): 0.24 | learning rate: 1.296E-04 | global batch size: 256 | lm loss: 2.964359E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1047.969 | TFLOPs: 6.67 | +31: iteration 16310/ 37905 | consumed samples: 4175360 | consumed tokens: 8551137280 | elapsed time per iteration (s): 0.24 | learning rate: 1.296E-04 | global batch size: 256 | lm loss: 2.990491E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.191 | TFLOPs: 6.74 | +31: iteration 16320/ 37905 | consumed samples: 4177920 | consumed tokens: 8556380160 | elapsed time per iteration (s): 0.25 | learning rate: 1.295E-04 | global batch size: 256 | lm loss: 2.995518E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1027.289 | TFLOPs: 6.54 | +31: iteration 16330/ 37905 | consumed samples: 4180480 | consumed tokens: 8561623040 | elapsed time per iteration (s): 0.23 | learning rate: 1.294E-04 | global batch size: 256 | lm loss: 2.960599E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.268 | TFLOPs: 7.06 | +31: iteration 16340/ 37905 | consumed samples: 4183040 | consumed tokens: 8566865920 | elapsed time per iteration (s): 0.20 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 2.983355E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.864 | TFLOPs: 8.22 | +31: iteration 16350/ 37905 | consumed samples: 4185600 | consumed tokens: 8572108800 | elapsed time per iteration (s): 0.21 | learning rate: 1.293E-04 | global batch size: 256 | lm loss: 2.963157E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.402 | TFLOPs: 7.75 | +31: iteration 16360/ 37905 | consumed samples: 4188160 | consumed tokens: 8577351680 | elapsed time per iteration (s): 0.22 | learning rate: 1.292E-04 | global batch size: 256 | lm loss: 2.984136E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.911 | TFLOPs: 7.57 | +31: iteration 16370/ 37905 | consumed samples: 4190720 | consumed tokens: 8582594560 | elapsed time per iteration (s): 0.21 | learning rate: 1.291E-04 | global batch size: 256 | lm loss: 2.994491E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1214.010 | TFLOPs: 7.73 | +31: iteration 16380/ 37905 | consumed samples: 4193280 | consumed tokens: 8587837440 | elapsed time per iteration (s): 0.20 | learning rate: 1.290E-04 | global batch size: 256 | lm loss: 2.995810E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.349 | TFLOPs: 8.24 | +31: iteration 16390/ 37905 | consumed samples: 4195840 | consumed tokens: 8593080320 | elapsed time per iteration (s): 0.24 | learning rate: 1.290E-04 | global batch size: 256 | lm loss: 2.973470E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.782 | TFLOPs: 6.76 | +31: iteration 16400/ 37905 | consumed samples: 4198400 | consumed tokens: 8598323200 | elapsed time per iteration (s): 0.20 | learning rate: 1.289E-04 | global batch size: 256 | lm loss: 2.989734E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.269 | TFLOPs: 8.36 | +31: iteration 16410/ 37905 | consumed samples: 4200960 | consumed tokens: 8603566080 | elapsed time per iteration (s): 0.19 | learning rate: 1.288E-04 | global batch size: 256 | lm loss: 2.964745E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1322.899 | TFLOPs: 8.43 | +31: iteration 16420/ 37905 | consumed samples: 4203520 | consumed tokens: 8608808960 | elapsed time per iteration (s): 0.22 | learning rate: 1.288E-04 | global batch size: 256 | lm loss: 2.961827E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.696 | TFLOPs: 7.42 | +31: iteration 16430/ 37905 | consumed samples: 4206080 | consumed tokens: 8614051840 | elapsed time per iteration (s): 0.25 | learning rate: 1.287E-04 | global batch size: 256 | lm loss: 2.977606E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.813 | TFLOPs: 6.58 | +31: iteration 16440/ 37905 | consumed samples: 4208640 | consumed tokens: 8619294720 | elapsed time per iteration (s): 0.22 | learning rate: 1.286E-04 | global batch size: 256 | lm loss: 2.972137E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.609 | TFLOPs: 7.54 | +31: iteration 16450/ 37905 | consumed samples: 4211200 | consumed tokens: 8624537600 | elapsed time per iteration (s): 0.24 | learning rate: 1.285E-04 | global batch size: 256 | lm loss: 2.952603E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.382 | TFLOPs: 6.92 | +31: iteration 16460/ 37905 | consumed samples: 4213760 | consumed tokens: 8629780480 | elapsed time per iteration (s): 0.24 | learning rate: 1.285E-04 | global batch size: 256 | lm loss: 2.958442E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.139 | TFLOPs: 6.82 | +31: iteration 16470/ 37905 | consumed samples: 4216320 | consumed tokens: 8635023360 | elapsed time per iteration (s): 0.22 | learning rate: 1.284E-04 | global batch size: 256 | lm loss: 2.976682E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.617 | TFLOPs: 7.42 | +31: iteration 16480/ 37905 | consumed samples: 4218880 | consumed tokens: 8640266240 | elapsed time per iteration (s): 0.21 | learning rate: 1.283E-04 | global batch size: 256 | lm loss: 3.007752E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.685 | TFLOPs: 7.95 | +31: iteration 16490/ 37905 | consumed samples: 4221440 | consumed tokens: 8645509120 | elapsed time per iteration (s): 0.19 | learning rate: 1.282E-04 | global batch size: 256 | lm loss: 2.964701E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1360.726 | TFLOPs: 8.67 | +31: iteration 16500/ 37905 | consumed samples: 4224000 | consumed tokens: 8650752000 | elapsed time per iteration (s): 0.22 | learning rate: 1.282E-04 | global batch size: 256 | lm loss: 2.988177E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.481 | TFLOPs: 7.42 | +31: iteration 16510/ 37905 | consumed samples: 4226560 | consumed tokens: 8655994880 | elapsed time per iteration (s): 0.22 | learning rate: 1.281E-04 | global batch size: 256 | lm loss: 2.966971E+00 | grad norm: 0.299 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.348 | TFLOPs: 7.33 | +31: iteration 16520/ 37905 | consumed samples: 4229120 | consumed tokens: 8661237760 | elapsed time per iteration (s): 0.21 | learning rate: 1.280E-04 | global batch size: 256 | lm loss: 2.979805E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.023 | TFLOPs: 7.73 | +31: iteration 16530/ 37905 | consumed samples: 4231680 | consumed tokens: 8666480640 | elapsed time per iteration (s): 0.24 | learning rate: 1.279E-04 | global batch size: 256 | lm loss: 2.977701E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.086 | TFLOPs: 6.84 | +31: iteration 16540/ 37905 | consumed samples: 4234240 | consumed tokens: 8671723520 | elapsed time per iteration (s): 0.19 | learning rate: 1.279E-04 | global batch size: 256 | lm loss: 2.960142E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.404 | TFLOPs: 8.47 | +31: iteration 16550/ 37905 | consumed samples: 4236800 | consumed tokens: 8676966400 | elapsed time per iteration (s): 0.26 | learning rate: 1.278E-04 | global batch size: 256 | lm loss: 2.987590E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 987.820 | TFLOPs: 6.29 | +31: iteration 16560/ 37905 | consumed samples: 4239360 | consumed tokens: 8682209280 | elapsed time per iteration (s): 0.24 | learning rate: 1.277E-04 | global batch size: 256 | lm loss: 2.941714E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.237 | TFLOPs: 6.82 | +31: iteration 16570/ 37905 | consumed samples: 4241920 | consumed tokens: 8687452160 | elapsed time per iteration (s): 0.19 | learning rate: 1.277E-04 | global batch size: 256 | lm loss: 2.946439E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1327.157 | TFLOPs: 8.45 | +31: iteration 16580/ 37905 | consumed samples: 4244480 | consumed tokens: 8692695040 | elapsed time per iteration (s): 0.25 | learning rate: 1.276E-04 | global batch size: 256 | lm loss: 2.995492E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.681 | TFLOPs: 6.65 | +31: iteration 16590/ 37905 | consumed samples: 4247040 | consumed tokens: 8697937920 | elapsed time per iteration (s): 0.25 | learning rate: 1.275E-04 | global batch size: 256 | lm loss: 2.987814E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.583 | TFLOPs: 6.64 | +31: iteration 16600/ 37905 | consumed samples: 4249600 | consumed tokens: 8703180800 | elapsed time per iteration (s): 0.25 | learning rate: 1.274E-04 | global batch size: 256 | lm loss: 2.930186E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.623 | TFLOPs: 6.56 | +31: iteration 16610/ 37905 | consumed samples: 4252160 | consumed tokens: 8708423680 | elapsed time per iteration (s): 0.20 | learning rate: 1.274E-04 | global batch size: 256 | lm loss: 3.000425E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.520 | TFLOPs: 8.26 | +31: iteration 16620/ 37905 | consumed samples: 4254720 | consumed tokens: 8713666560 | elapsed time per iteration (s): 0.25 | learning rate: 1.273E-04 | global batch size: 256 | lm loss: 2.977260E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.798 | TFLOPs: 6.60 | +31: iteration 16630/ 37905 | consumed samples: 4257280 | consumed tokens: 8718909440 | elapsed time per iteration (s): 0.23 | learning rate: 1.272E-04 | global batch size: 256 | lm loss: 2.979466E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.508 | TFLOPs: 7.06 | +31: iteration 16640/ 37905 | consumed samples: 4259840 | consumed tokens: 8724152320 | elapsed time per iteration (s): 0.20 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 2.963962E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.529 | TFLOPs: 8.16 | +31: iteration 16650/ 37905 | consumed samples: 4262400 | consumed tokens: 8729395200 | elapsed time per iteration (s): 0.20 | learning rate: 1.271E-04 | global batch size: 256 | lm loss: 2.957776E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.822 | TFLOPs: 8.09 | +31: iteration 16660/ 37905 | consumed samples: 4264960 | consumed tokens: 8734638080 | elapsed time per iteration (s): 0.21 | learning rate: 1.270E-04 | global batch size: 256 | lm loss: 2.964798E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.384 | TFLOPs: 7.84 | +31: iteration 16670/ 37905 | consumed samples: 4267520 | consumed tokens: 8739880960 | elapsed time per iteration (s): 0.23 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 2.947847E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.561 | TFLOPs: 7.11 | +31: iteration 16680/ 37905 | consumed samples: 4270080 | consumed tokens: 8745123840 | elapsed time per iteration (s): 0.22 | learning rate: 1.269E-04 | global batch size: 256 | lm loss: 2.981308E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.933 | TFLOPs: 7.50 | +31: iteration 16690/ 37905 | consumed samples: 4272640 | consumed tokens: 8750366720 | elapsed time per iteration (s): 0.22 | learning rate: 1.268E-04 | global batch size: 256 | lm loss: 2.941760E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.317 | TFLOPs: 7.33 | +31: iteration 16700/ 37905 | consumed samples: 4275200 | consumed tokens: 8755609600 | elapsed time per iteration (s): 0.20 | learning rate: 1.267E-04 | global batch size: 256 | lm loss: 2.977681E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.602 | TFLOPs: 8.31 | +31: iteration 16710/ 37905 | consumed samples: 4277760 | consumed tokens: 8760852480 | elapsed time per iteration (s): 0.20 | learning rate: 1.266E-04 | global batch size: 256 | lm loss: 2.971881E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.620 | TFLOPs: 8.02 | +31: iteration 16720/ 37905 | consumed samples: 4280320 | consumed tokens: 8766095360 | elapsed time per iteration (s): 0.19 | learning rate: 1.266E-04 | global batch size: 256 | lm loss: 2.912779E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.836 | TFLOPs: 8.55 | +31: iteration 16730/ 37905 | consumed samples: 4282880 | consumed tokens: 8771338240 | elapsed time per iteration (s): 0.21 | learning rate: 1.265E-04 | global batch size: 256 | lm loss: 3.006902E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.367 | TFLOPs: 7.60 | +31: iteration 16740/ 37905 | consumed samples: 4285440 | consumed tokens: 8776581120 | elapsed time per iteration (s): 0.19 | learning rate: 1.264E-04 | global batch size: 256 | lm loss: 2.971291E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1351.243 | TFLOPs: 8.61 | +31: iteration 16750/ 37905 | consumed samples: 4288000 | consumed tokens: 8781824000 | elapsed time per iteration (s): 0.23 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 2.981719E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.852 | TFLOPs: 7.04 | +31: iteration 16760/ 37905 | consumed samples: 4290560 | consumed tokens: 8787066880 | elapsed time per iteration (s): 0.21 | learning rate: 1.263E-04 | global batch size: 256 | lm loss: 2.969476E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.902 | TFLOPs: 7.69 | +31: iteration 16770/ 37905 | consumed samples: 4293120 | consumed tokens: 8792309760 | elapsed time per iteration (s): 0.21 | learning rate: 1.262E-04 | global batch size: 256 | lm loss: 2.943270E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.920 | TFLOPs: 7.72 | +31: iteration 16780/ 37905 | consumed samples: 4295680 | consumed tokens: 8797552640 | elapsed time per iteration (s): 0.22 | learning rate: 1.261E-04 | global batch size: 256 | lm loss: 2.978374E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.893 | TFLOPs: 7.32 | +31: iteration 16790/ 37905 | consumed samples: 4298240 | consumed tokens: 8802795520 | elapsed time per iteration (s): 0.21 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 2.944170E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.842 | TFLOPs: 7.65 | +31: iteration 16800/ 37905 | consumed samples: 4300800 | consumed tokens: 8808038400 | elapsed time per iteration (s): 0.23 | learning rate: 1.260E-04 | global batch size: 256 | lm loss: 2.975442E+00 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.309 | TFLOPs: 7.22 | +31: iteration 16810/ 37905 | consumed samples: 4303360 | consumed tokens: 8813281280 | elapsed time per iteration (s): 0.22 | learning rate: 1.259E-04 | global batch size: 256 | lm loss: 2.938580E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.189 | TFLOPs: 7.45 | +31: iteration 16820/ 37905 | consumed samples: 4305920 | consumed tokens: 8818524160 | elapsed time per iteration (s): 0.22 | learning rate: 1.258E-04 | global batch size: 256 | lm loss: 2.939631E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.875 | TFLOPs: 7.54 | +31: iteration 16830/ 37905 | consumed samples: 4308480 | consumed tokens: 8823767040 | elapsed time per iteration (s): 0.23 | learning rate: 1.258E-04 | global batch size: 256 | lm loss: 2.960908E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.362 | TFLOPs: 7.03 | +31: iteration 16840/ 37905 | consumed samples: 4311040 | consumed tokens: 8829009920 | elapsed time per iteration (s): 0.20 | learning rate: 1.257E-04 | global batch size: 256 | lm loss: 2.942253E+00 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.187 | TFLOPs: 7.98 | +31: iteration 16850/ 37905 | consumed samples: 4313600 | consumed tokens: 8834252800 | elapsed time per iteration (s): 0.23 | learning rate: 1.256E-04 | global batch size: 256 | lm loss: 2.961261E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.403 | TFLOPs: 6.94 | +31: iteration 16860/ 37905 | consumed samples: 4316160 | consumed tokens: 8839495680 | elapsed time per iteration (s): 0.19 | learning rate: 1.255E-04 | global batch size: 256 | lm loss: 2.977090E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1375.604 | TFLOPs: 8.76 | +31: iteration 16870/ 37905 | consumed samples: 4318720 | consumed tokens: 8844738560 | elapsed time per iteration (s): 0.21 | learning rate: 1.255E-04 | global batch size: 256 | lm loss: 2.981733E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.102 | TFLOPs: 7.92 | +31: iteration 16880/ 37905 | consumed samples: 4321280 | consumed tokens: 8849981440 | elapsed time per iteration (s): 0.23 | learning rate: 1.254E-04 | global batch size: 256 | lm loss: 2.943654E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.274 | TFLOPs: 7.05 | +31: iteration 16890/ 37905 | consumed samples: 4323840 | consumed tokens: 8855224320 | elapsed time per iteration (s): 0.22 | learning rate: 1.253E-04 | global batch size: 256 | lm loss: 2.981570E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.517 | TFLOPs: 7.51 | +31: iteration 16900/ 37905 | consumed samples: 4326400 | consumed tokens: 8860467200 | elapsed time per iteration (s): 0.22 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 2.950939E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.617 | TFLOPs: 7.54 | +31: iteration 16910/ 37905 | consumed samples: 4328960 | consumed tokens: 8865710080 | elapsed time per iteration (s): 0.21 | learning rate: 1.252E-04 | global batch size: 256 | lm loss: 2.941342E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.563 | TFLOPs: 7.86 | +31: iteration 16920/ 37905 | consumed samples: 4331520 | consumed tokens: 8870952960 | elapsed time per iteration (s): 0.20 | learning rate: 1.251E-04 | global batch size: 256 | lm loss: 2.940877E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.663 | TFLOPs: 8.10 | +31: iteration 16930/ 37905 | consumed samples: 4334080 | consumed tokens: 8876195840 | elapsed time per iteration (s): 0.23 | learning rate: 1.250E-04 | global batch size: 256 | lm loss: 2.946105E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1137.581 | TFLOPs: 7.25 | +31: iteration 16940/ 37905 | consumed samples: 4336640 | consumed tokens: 8881438720 | elapsed time per iteration (s): 0.21 | learning rate: 1.249E-04 | global batch size: 256 | lm loss: 2.965331E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.410 | TFLOPs: 7.67 | +31: iteration 16950/ 37905 | consumed samples: 4339200 | consumed tokens: 8886681600 | elapsed time per iteration (s): 0.23 | learning rate: 1.249E-04 | global batch size: 256 | lm loss: 2.938755E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.144 | TFLOPs: 7.19 | +31: iteration 16960/ 37905 | consumed samples: 4341760 | consumed tokens: 8891924480 | elapsed time per iteration (s): 0.23 | learning rate: 1.248E-04 | global batch size: 256 | lm loss: 2.960382E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.049 | TFLOPs: 7.11 | +31: iteration 16970/ 37905 | consumed samples: 4344320 | consumed tokens: 8897167360 | elapsed time per iteration (s): 0.19 | learning rate: 1.247E-04 | global batch size: 256 | lm loss: 2.956352E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1360.974 | TFLOPs: 8.67 | +31: iteration 16980/ 37905 | consumed samples: 4346880 | consumed tokens: 8902410240 | elapsed time per iteration (s): 0.22 | learning rate: 1.246E-04 | global batch size: 256 | lm loss: 2.999252E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.789 | TFLOPs: 7.47 | +31: iteration 16990/ 37905 | consumed samples: 4349440 | consumed tokens: 8907653120 | elapsed time per iteration (s): 0.23 | learning rate: 1.246E-04 | global batch size: 256 | lm loss: 2.981069E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.914 | TFLOPs: 6.95 | +31: iteration 17000/ 37905 | consumed samples: 4352000 | consumed tokens: 8912896000 | elapsed time per iteration (s): 0.21 | learning rate: 1.245E-04 | global batch size: 256 | lm loss: 2.981292E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.947 | TFLOPs: 7.85 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 17000 | lm loss value: 2.931289E+00 | lm loss PPL: 1.875179E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 17000 to checkpoints_83m + 0: [2022-11-24 15:11:55,555] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step17000 is begin to save! + 0: [2022-11-24 15:11:55,563] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,650] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,662] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,673] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,705] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,716] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,727] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,738] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,749] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:11:55,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:11:55,750] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step17000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:11:55,750] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:11:55,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:11:55,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:11:55,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:11:55,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,824] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +31: [2022-11-24 15:11:55,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,826] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,826] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,826] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:11:55,827] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,827] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:11:55,828] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,828] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +28: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,829] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,829] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +28: [2022-11-24 15:11:55,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:11:55,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +31: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +25: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,830] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,830] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +17: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +29: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +29: [2022-11-24 15:11:55,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:11:55,831] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,831] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +23: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +23: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +25: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,832] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:11:55,832] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:11:55,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +14: [2022-11-24 15:11:55,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,833] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +19: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 7: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +11: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,834] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,834] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:11:55,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:11:55,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,835] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +18: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 1: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +28: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,836] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,836] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:11:55,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +31: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +29: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,837] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:11:55,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +17: [2022-11-24 15:11:55,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:11:55,838] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,838] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +25: [2022-11-24 15:11:55,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:11:55,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,839] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,839] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:11:55,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 7: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,840] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,840] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +21: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +19: [2022-11-24 15:11:55,841] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,841] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:11:55,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:11:55,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,842] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,842] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 1: [2022-11-24 15:11:55,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:11:55,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +18: [2022-11-24 15:11:55,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +28: [2022-11-24 15:11:55,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,843] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +30: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:11:55,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:11:55,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +31: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,844] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:11:55,844] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:11:55,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +29: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +17: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,845] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,845] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:11:55,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:11:55,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,846] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:11:55,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +25: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +14: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,847] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 7: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 7: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,848] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,848] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:11:55,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +19: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:11:55,849] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,849] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:11:55,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:11:55,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +18: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,850] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 1: [2022-11-24 15:11:55,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +30: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:11:55,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,851] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,851] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +31: [2022-11-24 15:11:55,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:11:55,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:11:55,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:11:55,852] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,852] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +29: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,853] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,853] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:11:55,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +25: [2022-11-24 15:11:55,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,854] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,854] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:11:55,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:11:55,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,855] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:11:55,855] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:11:55,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +19: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:11:55,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:11:55,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:11:55,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:11:55,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 1: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +18: [2022-11-24 15:11:55,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +28: [2022-11-24 15:11:55,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +30: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +29: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:11:55,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +31: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +17: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:11:55,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +25: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:11:55,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:11:55,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:11:55,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:11:55,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 7: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +11: [2022-11-24 15:11:55,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +19: [2022-11-24 15:11:55,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:11:55,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:11:55,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +18: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +28: [2022-11-24 15:11:55,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +30: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 8: [2022-11-24 15:11:55,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:11:55,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +17: [2022-11-24 15:11:55,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:11:55,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +29: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +29: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +14: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: [2022-11-24 15:11:55,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:11:55,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +26: [2022-11-24 15:11:55,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 7: [2022-11-24 15:11:55,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +19: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:11:55,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:11:55,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:11:55,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +18: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 1: [2022-11-24 15:11:55,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +12: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:11:55,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +30: [2022-11-24 15:11:55,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +12: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +30: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +13: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +28: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +31: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +23: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +31: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +25: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +25: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +28: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +23: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +29: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +14: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +13: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +18: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 3: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +20: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +11: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 1: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 4: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +26: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +18: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +15: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +17: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +14: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 6: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +24: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +10: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +19: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +15: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +17: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +16: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +19: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +20: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +24: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +17: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 9: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +10: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +16: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 5: [2022-11-24 15:11:55,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 2: [2022-11-24 15:11:55,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:11:55,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:11:55,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +21: [2022-11-24 15:11:55,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +27: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:11:55,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +22: [2022-11-24 15:11:55,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! +30: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:11:55,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step17000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:11:55,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step17000 is ready now! + 0: successfully saved checkpoint at iteration 17000 to checkpoints_83m +31: time (ms) | save-checkpoint: 324.53 +31: iteration 17010/ 37905 | consumed samples: 4354560 | consumed tokens: 8918138880 | elapsed time per iteration (s): 0.22 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 2.970818E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.986 | TFLOPs: 7.41 | +31: iteration 17020/ 37905 | consumed samples: 4357120 | consumed tokens: 8923381760 | elapsed time per iteration (s): 0.20 | learning rate: 1.244E-04 | global batch size: 256 | lm loss: 2.992470E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.526 | TFLOPs: 8.26 | +31: iteration 17030/ 37905 | consumed samples: 4359680 | consumed tokens: 8928624640 | elapsed time per iteration (s): 0.22 | learning rate: 1.243E-04 | global batch size: 256 | lm loss: 2.983662E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.042 | TFLOPs: 7.32 | +31: iteration 17040/ 37905 | consumed samples: 4362240 | consumed tokens: 8933867520 | elapsed time per iteration (s): 0.21 | learning rate: 1.242E-04 | global batch size: 256 | lm loss: 2.983734E+00 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.606 | TFLOPs: 7.77 | +31: iteration 17050/ 37905 | consumed samples: 4364800 | consumed tokens: 8939110400 | elapsed time per iteration (s): 0.24 | learning rate: 1.241E-04 | global batch size: 256 | lm loss: 2.987517E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.645 | TFLOPs: 6.73 | +31: iteration 17060/ 37905 | consumed samples: 4367360 | consumed tokens: 8944353280 | elapsed time per iteration (s): 0.21 | learning rate: 1.241E-04 | global batch size: 256 | lm loss: 2.910985E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.858 | TFLOPs: 7.85 | +31: iteration 17070/ 37905 | consumed samples: 4369920 | consumed tokens: 8949596160 | elapsed time per iteration (s): 0.21 | learning rate: 1.240E-04 | global batch size: 256 | lm loss: 2.970517E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.294 | TFLOPs: 7.83 | +31: iteration 17080/ 37905 | consumed samples: 4372480 | consumed tokens: 8954839040 | elapsed time per iteration (s): 0.21 | learning rate: 1.239E-04 | global batch size: 256 | lm loss: 2.970598E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.925 | TFLOPs: 7.62 | +31: iteration 17090/ 37905 | consumed samples: 4375040 | consumed tokens: 8960081920 | elapsed time per iteration (s): 0.24 | learning rate: 1.238E-04 | global batch size: 256 | lm loss: 2.971754E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.538 | TFLOPs: 6.74 | +31: iteration 17100/ 37905 | consumed samples: 4377600 | consumed tokens: 8965324800 | elapsed time per iteration (s): 0.23 | learning rate: 1.238E-04 | global batch size: 256 | lm loss: 2.960198E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.155 | TFLOPs: 7.14 | +31: iteration 17110/ 37905 | consumed samples: 4380160 | consumed tokens: 8970567680 | elapsed time per iteration (s): 0.20 | learning rate: 1.237E-04 | global batch size: 256 | lm loss: 2.948421E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.627 | TFLOPs: 8.32 | +31: iteration 17120/ 37905 | consumed samples: 4382720 | consumed tokens: 8975810560 | elapsed time per iteration (s): 0.21 | learning rate: 1.236E-04 | global batch size: 256 | lm loss: 3.002859E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.374 | TFLOPs: 7.59 | +31: iteration 17130/ 37905 | consumed samples: 4385280 | consumed tokens: 8981053440 | elapsed time per iteration (s): 0.23 | learning rate: 1.235E-04 | global batch size: 256 | lm loss: 2.937824E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.515 | TFLOPs: 7.13 | +31: iteration 17140/ 37905 | consumed samples: 4387840 | consumed tokens: 8986296320 | elapsed time per iteration (s): 0.20 | learning rate: 1.235E-04 | global batch size: 256 | lm loss: 2.959562E+00 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.383 | TFLOPs: 8.07 | +31: iteration 17150/ 37905 | consumed samples: 4390400 | consumed tokens: 8991539200 | elapsed time per iteration (s): 0.19 | learning rate: 1.234E-04 | global batch size: 256 | lm loss: 2.966183E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.626 | TFLOPs: 8.38 | +31: iteration 17160/ 37905 | consumed samples: 4392960 | consumed tokens: 8996782080 | elapsed time per iteration (s): 0.22 | learning rate: 1.233E-04 | global batch size: 256 | lm loss: 2.958342E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.697 | TFLOPs: 7.42 | +31: iteration 17170/ 37905 | consumed samples: 4395520 | consumed tokens: 9002024960 | elapsed time per iteration (s): 0.21 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 2.986198E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.585 | TFLOPs: 7.65 | +31: iteration 17180/ 37905 | consumed samples: 4398080 | consumed tokens: 9007267840 | elapsed time per iteration (s): 0.21 | learning rate: 1.232E-04 | global batch size: 256 | lm loss: 2.951795E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.718 | TFLOPs: 7.62 | +31: iteration 17190/ 37905 | consumed samples: 4400640 | consumed tokens: 9012510720 | elapsed time per iteration (s): 0.20 | learning rate: 1.231E-04 | global batch size: 256 | lm loss: 2.984335E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1292.643 | TFLOPs: 8.23 | +31: iteration 17200/ 37905 | consumed samples: 4403200 | consumed tokens: 9017753600 | elapsed time per iteration (s): 0.21 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 2.913457E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.208 | TFLOPs: 7.66 | +31: iteration 17210/ 37905 | consumed samples: 4405760 | consumed tokens: 9022996480 | elapsed time per iteration (s): 0.29 | learning rate: 1.230E-04 | global batch size: 256 | lm loss: 2.939906E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 876.080 | TFLOPs: 5.58 | +31: iteration 17220/ 37905 | consumed samples: 4408320 | consumed tokens: 9028239360 | elapsed time per iteration (s): 0.26 | learning rate: 1.229E-04 | global batch size: 256 | lm loss: 2.934875E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.386 | TFLOPs: 6.37 | +31: iteration 17230/ 37905 | consumed samples: 4410880 | consumed tokens: 9033482240 | elapsed time per iteration (s): 0.22 | learning rate: 1.228E-04 | global batch size: 256 | lm loss: 2.988969E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.502 | TFLOPs: 7.43 | +31: iteration 17240/ 37905 | consumed samples: 4413440 | consumed tokens: 9038725120 | elapsed time per iteration (s): 0.22 | learning rate: 1.227E-04 | global batch size: 256 | lm loss: 2.985165E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.035 | TFLOPs: 7.45 | +31: iteration 17250/ 37905 | consumed samples: 4416000 | consumed tokens: 9043968000 | elapsed time per iteration (s): 0.24 | learning rate: 1.227E-04 | global batch size: 256 | lm loss: 2.953335E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.351 | TFLOPs: 6.68 | +31: iteration 17260/ 37905 | consumed samples: 4418560 | consumed tokens: 9049210880 | elapsed time per iteration (s): 0.22 | learning rate: 1.226E-04 | global batch size: 256 | lm loss: 2.957107E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.997 | TFLOPs: 7.51 | +31: iteration 17270/ 37905 | consumed samples: 4421120 | consumed tokens: 9054453760 | elapsed time per iteration (s): 0.24 | learning rate: 1.225E-04 | global batch size: 256 | lm loss: 2.981058E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.213 | TFLOPs: 6.80 | +31: iteration 17280/ 37905 | consumed samples: 4423680 | consumed tokens: 9059696640 | elapsed time per iteration (s): 0.21 | learning rate: 1.224E-04 | global batch size: 256 | lm loss: 2.966805E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.852 | TFLOPs: 7.79 | +31: iteration 17290/ 37905 | consumed samples: 4426240 | consumed tokens: 9064939520 | elapsed time per iteration (s): 0.24 | learning rate: 1.224E-04 | global batch size: 256 | lm loss: 2.969885E+00 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.809 | TFLOPs: 6.69 | +31: iteration 17300/ 37905 | consumed samples: 4428800 | consumed tokens: 9070182400 | elapsed time per iteration (s): 0.22 | learning rate: 1.223E-04 | global batch size: 256 | lm loss: 2.974933E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.435 | TFLOPs: 7.28 | +31: iteration 17310/ 37905 | consumed samples: 4431360 | consumed tokens: 9075425280 | elapsed time per iteration (s): 0.20 | learning rate: 1.222E-04 | global batch size: 256 | lm loss: 2.939141E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.818 | TFLOPs: 8.06 | +31: iteration 17320/ 37905 | consumed samples: 4433920 | consumed tokens: 9080668160 | elapsed time per iteration (s): 0.25 | learning rate: 1.221E-04 | global batch size: 256 | lm loss: 2.952231E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.490 | TFLOPs: 6.64 | +31: iteration 17330/ 37905 | consumed samples: 4436480 | consumed tokens: 9085911040 | elapsed time per iteration (s): 0.21 | learning rate: 1.221E-04 | global batch size: 256 | lm loss: 2.976744E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.213 | TFLOPs: 7.64 | +31: iteration 17340/ 37905 | consumed samples: 4439040 | consumed tokens: 9091153920 | elapsed time per iteration (s): 0.22 | learning rate: 1.220E-04 | global batch size: 256 | lm loss: 2.951221E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.373 | TFLOPs: 7.30 | +31: iteration 17350/ 37905 | consumed samples: 4441600 | consumed tokens: 9096396800 | elapsed time per iteration (s): 0.22 | learning rate: 1.219E-04 | global batch size: 256 | lm loss: 2.938083E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.693 | TFLOPs: 7.40 | +31: iteration 17360/ 37905 | consumed samples: 4444160 | consumed tokens: 9101639680 | elapsed time per iteration (s): 0.23 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 2.925435E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.025 | TFLOPs: 7.22 | +31: iteration 17370/ 37905 | consumed samples: 4446720 | consumed tokens: 9106882560 | elapsed time per iteration (s): 0.24 | learning rate: 1.218E-04 | global batch size: 256 | lm loss: 2.937866E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.926 | TFLOPs: 6.81 | +31: iteration 17380/ 37905 | consumed samples: 4449280 | consumed tokens: 9112125440 | elapsed time per iteration (s): 0.21 | learning rate: 1.217E-04 | global batch size: 256 | lm loss: 2.970391E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.833 | TFLOPs: 7.79 | +31: iteration 17390/ 37905 | consumed samples: 4451840 | consumed tokens: 9117368320 | elapsed time per iteration (s): 0.21 | learning rate: 1.216E-04 | global batch size: 256 | lm loss: 2.995929E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.230 | TFLOPs: 7.74 | +31: iteration 17400/ 37905 | consumed samples: 4454400 | consumed tokens: 9122611200 | elapsed time per iteration (s): 0.22 | learning rate: 1.215E-04 | global batch size: 256 | lm loss: 2.963779E+00 | grad norm: 0.289 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.479 | TFLOPs: 7.29 | +31: iteration 17410/ 37905 | consumed samples: 4456960 | consumed tokens: 9127854080 | elapsed time per iteration (s): 0.24 | learning rate: 1.215E-04 | global batch size: 256 | lm loss: 2.953564E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.859 | TFLOPs: 6.75 | +31: iteration 17420/ 37905 | consumed samples: 4459520 | consumed tokens: 9133096960 | elapsed time per iteration (s): 0.21 | learning rate: 1.214E-04 | global batch size: 256 | lm loss: 2.956468E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.909 | TFLOPs: 7.86 | +31: iteration 17430/ 37905 | consumed samples: 4462080 | consumed tokens: 9138339840 | elapsed time per iteration (s): 0.23 | learning rate: 1.213E-04 | global batch size: 256 | lm loss: 2.976859E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.854 | TFLOPs: 7.09 | +31: iteration 17440/ 37905 | consumed samples: 4464640 | consumed tokens: 9143582720 | elapsed time per iteration (s): 0.25 | learning rate: 1.213E-04 | global batch size: 256 | lm loss: 2.941574E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1040.685 | TFLOPs: 6.63 | +31: iteration 17450/ 37905 | consumed samples: 4467200 | consumed tokens: 9148825600 | elapsed time per iteration (s): 0.21 | learning rate: 1.212E-04 | global batch size: 256 | lm loss: 2.973847E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.120 | TFLOPs: 7.75 | +31: iteration 17460/ 37905 | consumed samples: 4469760 | consumed tokens: 9154068480 | elapsed time per iteration (s): 0.22 | learning rate: 1.211E-04 | global batch size: 256 | lm loss: 2.981588E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.583 | TFLOPs: 7.46 | +31: iteration 17470/ 37905 | consumed samples: 4472320 | consumed tokens: 9159311360 | elapsed time per iteration (s): 0.21 | learning rate: 1.210E-04 | global batch size: 256 | lm loss: 2.927484E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.512 | TFLOPs: 7.64 | +31: iteration 17480/ 37905 | consumed samples: 4474880 | consumed tokens: 9164554240 | elapsed time per iteration (s): 0.22 | learning rate: 1.210E-04 | global batch size: 256 | lm loss: 2.967677E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.285 | TFLOPs: 7.40 | +31: iteration 17490/ 37905 | consumed samples: 4477440 | consumed tokens: 9169797120 | elapsed time per iteration (s): 0.22 | learning rate: 1.209E-04 | global batch size: 256 | lm loss: 2.987754E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.473 | TFLOPs: 7.32 | +31: iteration 17500/ 37905 | consumed samples: 4480000 | consumed tokens: 9175040000 | elapsed time per iteration (s): 0.20 | learning rate: 1.208E-04 | global batch size: 256 | lm loss: 2.938231E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.829 | TFLOPs: 8.21 | +31: iteration 17510/ 37905 | consumed samples: 4482560 | consumed tokens: 9180282880 | elapsed time per iteration (s): 0.23 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 2.931727E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.401 | TFLOPs: 7.03 | +31: iteration 17520/ 37905 | consumed samples: 4485120 | consumed tokens: 9185525760 | elapsed time per iteration (s): 0.21 | learning rate: 1.207E-04 | global batch size: 256 | lm loss: 2.962190E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.388 | TFLOPs: 7.77 | +31: iteration 17530/ 37905 | consumed samples: 4487680 | consumed tokens: 9190768640 | elapsed time per iteration (s): 0.20 | learning rate: 1.206E-04 | global batch size: 256 | lm loss: 2.996508E+00 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.973 | TFLOPs: 7.96 | +31: iteration 17540/ 37905 | consumed samples: 4490240 | consumed tokens: 9196011520 | elapsed time per iteration (s): 0.20 | learning rate: 1.205E-04 | global batch size: 256 | lm loss: 3.003707E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1262.112 | TFLOPs: 8.04 | +31: iteration 17550/ 37905 | consumed samples: 4492800 | consumed tokens: 9201254400 | elapsed time per iteration (s): 0.21 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 2.967567E+00 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.033 | TFLOPs: 7.78 | +31: iteration 17560/ 37905 | consumed samples: 4495360 | consumed tokens: 9206497280 | elapsed time per iteration (s): 0.21 | learning rate: 1.204E-04 | global batch size: 256 | lm loss: 2.945524E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1198.773 | TFLOPs: 7.63 | +31: iteration 17570/ 37905 | consumed samples: 4497920 | consumed tokens: 9211740160 | elapsed time per iteration (s): 0.22 | learning rate: 1.203E-04 | global batch size: 256 | lm loss: 2.945645E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.904 | TFLOPs: 7.34 | +31: iteration 17580/ 37905 | consumed samples: 4500480 | consumed tokens: 9216983040 | elapsed time per iteration (s): 0.22 | learning rate: 1.202E-04 | global batch size: 256 | lm loss: 2.977739E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.485 | TFLOPs: 7.27 | +31: iteration 17590/ 37905 | consumed samples: 4503040 | consumed tokens: 9222225920 | elapsed time per iteration (s): 0.26 | learning rate: 1.201E-04 | global batch size: 256 | lm loss: 2.938668E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 973.323 | TFLOPs: 6.20 | +31: iteration 17600/ 37905 | consumed samples: 4505600 | consumed tokens: 9227468800 | elapsed time per iteration (s): 0.20 | learning rate: 1.201E-04 | global batch size: 256 | lm loss: 2.980879E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.486 | TFLOPs: 8.00 | +31: iteration 17610/ 37905 | consumed samples: 4508160 | consumed tokens: 9232711680 | elapsed time per iteration (s): 0.27 | learning rate: 1.200E-04 | global batch size: 256 | lm loss: 2.964936E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 939.786 | TFLOPs: 5.99 | +31: iteration 17620/ 37905 | consumed samples: 4510720 | consumed tokens: 9237954560 | elapsed time per iteration (s): 0.21 | learning rate: 1.199E-04 | global batch size: 256 | lm loss: 2.978936E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.464 | TFLOPs: 7.80 | +31: iteration 17630/ 37905 | consumed samples: 4513280 | consumed tokens: 9243197440 | elapsed time per iteration (s): 0.22 | learning rate: 1.198E-04 | global batch size: 256 | lm loss: 2.949251E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.802 | TFLOPs: 7.56 | +31: iteration 17640/ 37905 | consumed samples: 4515840 | consumed tokens: 9248440320 | elapsed time per iteration (s): 0.22 | learning rate: 1.198E-04 | global batch size: 256 | lm loss: 2.937116E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.958 | TFLOPs: 7.56 | +31: iteration 17650/ 37905 | consumed samples: 4518400 | consumed tokens: 9253683200 | elapsed time per iteration (s): 0.24 | learning rate: 1.197E-04 | global batch size: 256 | lm loss: 2.975475E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.749 | TFLOPs: 6.72 | +31: iteration 17660/ 37905 | consumed samples: 4520960 | consumed tokens: 9258926080 | elapsed time per iteration (s): 0.21 | learning rate: 1.196E-04 | global batch size: 256 | lm loss: 2.976815E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.128 | TFLOPs: 7.79 | +31: iteration 17670/ 37905 | consumed samples: 4523520 | consumed tokens: 9264168960 | elapsed time per iteration (s): 0.21 | learning rate: 1.195E-04 | global batch size: 256 | lm loss: 2.919688E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.391 | TFLOPs: 7.93 | +31: iteration 17680/ 37905 | consumed samples: 4526080 | consumed tokens: 9269411840 | elapsed time per iteration (s): 0.23 | learning rate: 1.195E-04 | global batch size: 256 | lm loss: 2.955787E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.240 | TFLOPs: 7.10 | +31: iteration 17690/ 37905 | consumed samples: 4528640 | consumed tokens: 9274654720 | elapsed time per iteration (s): 0.20 | learning rate: 1.194E-04 | global batch size: 256 | lm loss: 2.998569E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.454 | TFLOPs: 8.09 | +31: iteration 17700/ 37905 | consumed samples: 4531200 | consumed tokens: 9279897600 | elapsed time per iteration (s): 0.21 | learning rate: 1.193E-04 | global batch size: 256 | lm loss: 2.967268E+00 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.306 | TFLOPs: 7.79 | +31: iteration 17710/ 37905 | consumed samples: 4533760 | consumed tokens: 9285140480 | elapsed time per iteration (s): 0.20 | learning rate: 1.193E-04 | global batch size: 256 | lm loss: 2.961774E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.015 | TFLOPs: 8.10 | +31: iteration 17720/ 37905 | consumed samples: 4536320 | consumed tokens: 9290383360 | elapsed time per iteration (s): 0.23 | learning rate: 1.192E-04 | global batch size: 256 | lm loss: 2.964603E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.704 | TFLOPs: 6.95 | +31: iteration 17730/ 37905 | consumed samples: 4538880 | consumed tokens: 9295626240 | elapsed time per iteration (s): 0.21 | learning rate: 1.191E-04 | global batch size: 256 | lm loss: 2.917288E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.187 | TFLOPs: 7.73 | +31: iteration 17740/ 37905 | consumed samples: 4541440 | consumed tokens: 9300869120 | elapsed time per iteration (s): 0.20 | learning rate: 1.190E-04 | global batch size: 256 | lm loss: 2.964184E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.052 | TFLOPs: 8.07 | +31: iteration 17750/ 37905 | consumed samples: 4544000 | consumed tokens: 9306112000 | elapsed time per iteration (s): 0.25 | learning rate: 1.190E-04 | global batch size: 256 | lm loss: 2.989779E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1005.718 | TFLOPs: 6.41 | +31: iteration 17760/ 37905 | consumed samples: 4546560 | consumed tokens: 9311354880 | elapsed time per iteration (s): 0.21 | learning rate: 1.189E-04 | global batch size: 256 | lm loss: 2.987228E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1214.688 | TFLOPs: 7.74 | +31: iteration 17770/ 37905 | consumed samples: 4549120 | consumed tokens: 9316597760 | elapsed time per iteration (s): 0.20 | learning rate: 1.188E-04 | global batch size: 256 | lm loss: 2.979454E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1306.157 | TFLOPs: 8.32 | +31: iteration 17780/ 37905 | consumed samples: 4551680 | consumed tokens: 9321840640 | elapsed time per iteration (s): 0.21 | learning rate: 1.187E-04 | global batch size: 256 | lm loss: 2.973632E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.010 | TFLOPs: 7.80 | +31: iteration 17790/ 37905 | consumed samples: 4554240 | consumed tokens: 9327083520 | elapsed time per iteration (s): 0.23 | learning rate: 1.187E-04 | global batch size: 256 | lm loss: 2.935030E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.993 | TFLOPs: 7.00 | +31: iteration 17800/ 37905 | consumed samples: 4556800 | consumed tokens: 9332326400 | elapsed time per iteration (s): 0.22 | learning rate: 1.186E-04 | global batch size: 256 | lm loss: 2.971404E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.913 | TFLOPs: 7.27 | +31: iteration 17810/ 37905 | consumed samples: 4559360 | consumed tokens: 9337569280 | elapsed time per iteration (s): 0.21 | learning rate: 1.185E-04 | global batch size: 256 | lm loss: 2.967387E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.360 | TFLOPs: 7.76 | +31: iteration 17820/ 37905 | consumed samples: 4561920 | consumed tokens: 9342812160 | elapsed time per iteration (s): 0.19 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 2.953045E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1365.021 | TFLOPs: 8.69 | +31: iteration 17830/ 37905 | consumed samples: 4564480 | consumed tokens: 9348055040 | elapsed time per iteration (s): 0.20 | learning rate: 1.184E-04 | global batch size: 256 | lm loss: 2.980418E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.496 | TFLOPs: 8.15 | +31: iteration 17840/ 37905 | consumed samples: 4567040 | consumed tokens: 9353297920 | elapsed time per iteration (s): 0.23 | learning rate: 1.183E-04 | global batch size: 256 | lm loss: 2.952674E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.207 | TFLOPs: 7.20 | +31: iteration 17850/ 37905 | consumed samples: 4569600 | consumed tokens: 9358540800 | elapsed time per iteration (s): 0.23 | learning rate: 1.182E-04 | global batch size: 256 | lm loss: 2.952066E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.571 | TFLOPs: 6.96 | +31: iteration 17860/ 37905 | consumed samples: 4572160 | consumed tokens: 9363783680 | elapsed time per iteration (s): 0.22 | learning rate: 1.181E-04 | global batch size: 256 | lm loss: 2.944073E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.926 | TFLOPs: 7.33 | +31: iteration 17870/ 37905 | consumed samples: 4574720 | consumed tokens: 9369026560 | elapsed time per iteration (s): 0.22 | learning rate: 1.181E-04 | global batch size: 256 | lm loss: 2.975352E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.604 | TFLOPs: 7.30 | +31: iteration 17880/ 37905 | consumed samples: 4577280 | consumed tokens: 9374269440 | elapsed time per iteration (s): 0.20 | learning rate: 1.180E-04 | global batch size: 256 | lm loss: 2.968487E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1260.793 | TFLOPs: 8.03 | +31: iteration 17890/ 37905 | consumed samples: 4579840 | consumed tokens: 9379512320 | elapsed time per iteration (s): 0.21 | learning rate: 1.179E-04 | global batch size: 256 | lm loss: 2.935005E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.679 | TFLOPs: 7.83 | +31: iteration 17900/ 37905 | consumed samples: 4582400 | consumed tokens: 9384755200 | elapsed time per iteration (s): 0.20 | learning rate: 1.178E-04 | global batch size: 256 | lm loss: 3.008563E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.632 | TFLOPs: 7.97 | +31: iteration 17910/ 37905 | consumed samples: 4584960 | consumed tokens: 9389998080 | elapsed time per iteration (s): 0.22 | learning rate: 1.178E-04 | global batch size: 256 | lm loss: 2.906273E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.914 | TFLOPs: 7.48 | +31: iteration 17920/ 37905 | consumed samples: 4587520 | consumed tokens: 9395240960 | elapsed time per iteration (s): 0.20 | learning rate: 1.177E-04 | global batch size: 256 | lm loss: 2.951894E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.016 | TFLOPs: 7.96 | +31: iteration 17930/ 37905 | consumed samples: 4590080 | consumed tokens: 9400483840 | elapsed time per iteration (s): 0.24 | learning rate: 1.176E-04 | global batch size: 256 | lm loss: 2.976368E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.485 | TFLOPs: 6.77 | +31: iteration 17940/ 37905 | consumed samples: 4592640 | consumed tokens: 9405726720 | elapsed time per iteration (s): 0.23 | learning rate: 1.175E-04 | global batch size: 256 | lm loss: 2.962941E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.881 | TFLOPs: 7.02 | +31: iteration 17950/ 37905 | consumed samples: 4595200 | consumed tokens: 9410969600 | elapsed time per iteration (s): 0.22 | learning rate: 1.175E-04 | global batch size: 256 | lm loss: 2.968133E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.097 | TFLOPs: 7.53 | +31: iteration 17960/ 37905 | consumed samples: 4597760 | consumed tokens: 9416212480 | elapsed time per iteration (s): 0.28 | learning rate: 1.174E-04 | global batch size: 256 | lm loss: 2.945827E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 901.544 | TFLOPs: 5.74 | +31: iteration 17970/ 37905 | consumed samples: 4600320 | consumed tokens: 9421455360 | elapsed time per iteration (s): 0.22 | learning rate: 1.173E-04 | global batch size: 256 | lm loss: 2.947139E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.611 | TFLOPs: 7.27 | +31: iteration 17980/ 37905 | consumed samples: 4602880 | consumed tokens: 9426698240 | elapsed time per iteration (s): 0.24 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 2.977731E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.783 | TFLOPs: 6.84 | +31: iteration 17990/ 37905 | consumed samples: 4605440 | consumed tokens: 9431941120 | elapsed time per iteration (s): 0.20 | learning rate: 1.172E-04 | global batch size: 256 | lm loss: 2.957493E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.541 | TFLOPs: 8.10 | + 0: [2022-11-24 15:15:36,170] [INFO] [logging.py:68:log_dist] [Rank 0] step=18000, skipped=0, lr=[0.00011709785950890625, 0.00011709785950890625, 0.00011709785950890625], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 18000/ 37905 | consumed samples: 4608000 | consumed tokens: 9437184000 | elapsed time per iteration (s): 0.25 | learning rate: 1.171E-04 | global batch size: 256 | lm loss: 2.969887E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1014.664 | TFLOPs: 6.46 | + 0: steps: 18000 loss: 2.9295 iter time (s): 0.218 samples/sec: 1176.138 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 18000 | lm loss value: 2.753893E+00 | lm loss PPL: 1.570364E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 18000 to checkpoints_83m + 0: [2022-11-24 15:15:36,357] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step18000 is begin to save! + 0: [2022-11-24 15:15:36,368] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,440] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,452] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,462] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,473] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,506] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,517] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,528] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,539] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,551] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:15:36,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:15:36,552] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step18000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:15:36,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:15:36,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:15:36,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step18000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:15:36,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,626] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,626] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:15:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 8: [2022-11-24 15:15:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,627] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:15:36,627] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +24: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,628] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:15:36,628] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +11: [2022-11-24 15:15:36,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:15:36,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,629] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:15:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:15:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 5: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +13: [2022-11-24 15:15:36,630] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +15: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +26: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:15:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +22: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:15:36,631] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:15:36,632] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +17: [2022-11-24 15:15:36,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +17: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:15:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +12: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 8: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,633] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +31: [2022-11-24 15:15:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:15:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,634] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +24: [2022-11-24 15:15:36,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +11: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:15:36,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:15:36,635] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,635] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,636] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,636] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:15:36,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:15:36,637] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,637] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +15: [2022-11-24 15:15:36,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 5: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +19: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +26: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +22: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +22: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 2: [2022-11-24 15:15:36,638] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:15:36,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:15:36,639] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 8: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:15:36,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +12: [2022-11-24 15:15:36,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,640] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:15:36,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:15:36,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:15:36,641] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +24: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +11: [2022-11-24 15:15:36,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +31: [2022-11-24 15:15:36,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:15:36,642] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:15:36,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:15:36,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +27: [2022-11-24 15:15:36,643] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:15:36,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,644] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +13: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,644] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 5: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +26: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,645] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:15:36,646] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +22: [2022-11-24 15:15:36,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,646] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 15:15:36,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:15:36,646] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,646] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +17: [2022-11-24 15:15:36,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 2: [2022-11-24 15:15:36,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +12: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:15:36,647] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,647] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:15:36,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,648] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,649] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,649] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,649] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +11: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,649] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,649] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,650] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:15:36,650] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:15:36,650] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,650] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,650] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,651] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +28: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,651] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:15:36,651] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:15:36,651] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,651] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:15:36,652] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,652] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +15: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 5: [2022-11-24 15:15:36,652] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,652] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +26: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,652] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,652] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +22: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +22: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:15:36,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +17: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 2: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:15:36,653] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +12: [2022-11-24 15:15:36,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:15:36,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:15:36,654] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 8: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:15:36,655] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,655] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:15:36,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +24: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:15:36,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +11: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,656] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,656] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:15:36,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:15:36,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:15:36,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +27: [2022-11-24 15:15:36,657] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +15: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,658] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +26: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,659] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +22: [2022-11-24 15:15:36,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:15:36,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:15:36,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:15:36,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 2: [2022-11-24 15:15:36,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,660] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +17: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +12: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:15:36,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 8: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,661] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:15:36,661] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:15:36,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:15:36,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,662] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +24: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:15:36,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:15:36,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +11: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,663] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:15:36,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:15:36,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,664] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +28: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 5: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,665] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +15: [2022-11-24 15:15:36,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +22: [2022-11-24 15:15:36,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +22: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:15:36,666] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 2: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:15:36,667] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +17: [2022-11-24 15:15:36,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:15:36,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +12: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 8: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,668] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:15:36,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:15:36,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +24: [2022-11-24 15:15:36,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,669] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:15:36,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:15:36,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +11: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,670] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:15:36,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:15:36,671] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:15:36,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +15: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:15:36,672] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 5: [2022-11-24 15:15:36,672] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +22: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +26: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +12: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +25: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 8: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +25: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +13: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +15: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +20: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 7: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +29: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 2: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +14: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +23: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +11: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +12: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +27: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +23: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +17: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,673] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +19: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +14: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 3: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 6: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +26: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +29: [2022-11-24 15:15:36,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +10: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +26: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +10: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +24: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +18: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +17: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +18: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 9: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +31: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 4: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +31: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 1: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +30: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,674] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +16: [2022-11-24 15:15:36,674] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:15:36,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:15:36,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:15:36,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +28: [2022-11-24 15:15:36,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! +21: [2022-11-24 15:15:36,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:15:36,675] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step18000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:15:36,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step18000 is ready now! + 0: successfully saved checkpoint at iteration 18000 to checkpoints_83m +31: time (ms) | save-checkpoint: 322.71 +31: iteration 18010/ 37905 | consumed samples: 4610560 | consumed tokens: 9442426880 | elapsed time per iteration (s): 0.24 | learning rate: 1.170E-04 | global batch size: 256 | lm loss: 2.980101E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.787 | TFLOPs: 6.79 | +31: iteration 18020/ 37905 | consumed samples: 4613120 | consumed tokens: 9447669760 | elapsed time per iteration (s): 0.21 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 2.966353E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.519 | TFLOPs: 7.93 | +31: iteration 18030/ 37905 | consumed samples: 4615680 | consumed tokens: 9452912640 | elapsed time per iteration (s): 0.22 | learning rate: 1.169E-04 | global batch size: 256 | lm loss: 2.935490E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.815 | TFLOPs: 7.45 | +31: iteration 18040/ 37905 | consumed samples: 4618240 | consumed tokens: 9458155520 | elapsed time per iteration (s): 0.22 | learning rate: 1.168E-04 | global batch size: 256 | lm loss: 2.961452E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.342 | TFLOPs: 7.26 | +31: iteration 18050/ 37905 | consumed samples: 4620800 | consumed tokens: 9463398400 | elapsed time per iteration (s): 0.21 | learning rate: 1.167E-04 | global batch size: 256 | lm loss: 2.964520E+00 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1198.991 | TFLOPs: 7.64 | +31: iteration 18060/ 37905 | consumed samples: 4623360 | consumed tokens: 9468641280 | elapsed time per iteration (s): 0.23 | learning rate: 1.167E-04 | global batch size: 256 | lm loss: 2.929022E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.855 | TFLOPs: 7.13 | +31: iteration 18070/ 37905 | consumed samples: 4625920 | consumed tokens: 9473884160 | elapsed time per iteration (s): 0.22 | learning rate: 1.166E-04 | global batch size: 256 | lm loss: 2.977463E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.605 | TFLOPs: 7.43 | +31: iteration 18080/ 37905 | consumed samples: 4628480 | consumed tokens: 9479127040 | elapsed time per iteration (s): 0.22 | learning rate: 1.165E-04 | global batch size: 256 | lm loss: 2.940624E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.696 | TFLOPs: 7.28 | +31: iteration 18090/ 37905 | consumed samples: 4631040 | consumed tokens: 9484369920 | elapsed time per iteration (s): 0.24 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 2.974058E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.497 | TFLOPs: 6.84 | +31: iteration 18100/ 37905 | consumed samples: 4633600 | consumed tokens: 9489612800 | elapsed time per iteration (s): 0.23 | learning rate: 1.164E-04 | global batch size: 256 | lm loss: 2.957010E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.505 | TFLOPs: 7.19 | +31: iteration 18110/ 37905 | consumed samples: 4636160 | consumed tokens: 9494855680 | elapsed time per iteration (s): 0.20 | learning rate: 1.163E-04 | global batch size: 256 | lm loss: 2.988076E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.861 | TFLOPs: 8.22 | +31: iteration 18120/ 37905 | consumed samples: 4638720 | consumed tokens: 9500098560 | elapsed time per iteration (s): 0.22 | learning rate: 1.162E-04 | global batch size: 256 | lm loss: 2.992768E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.765 | TFLOPs: 7.48 | +31: iteration 18130/ 37905 | consumed samples: 4641280 | consumed tokens: 9505341440 | elapsed time per iteration (s): 0.22 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 2.977287E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.864 | TFLOPs: 7.37 | +31: iteration 18140/ 37905 | consumed samples: 4643840 | consumed tokens: 9510584320 | elapsed time per iteration (s): 0.20 | learning rate: 1.161E-04 | global batch size: 256 | lm loss: 2.931438E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.748 | TFLOPs: 8.04 | +31: iteration 18150/ 37905 | consumed samples: 4646400 | consumed tokens: 9515827200 | elapsed time per iteration (s): 0.19 | learning rate: 1.160E-04 | global batch size: 256 | lm loss: 2.924941E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.056 | TFLOPs: 8.57 | +31: iteration 18160/ 37905 | consumed samples: 4648960 | consumed tokens: 9521070080 | elapsed time per iteration (s): 0.20 | learning rate: 1.159E-04 | global batch size: 256 | lm loss: 2.911777E+00 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.425 | TFLOPs: 8.10 | +31: iteration 18170/ 37905 | consumed samples: 4651520 | consumed tokens: 9526312960 | elapsed time per iteration (s): 0.20 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 2.933569E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.401 | TFLOPs: 8.14 | +31: iteration 18180/ 37905 | consumed samples: 4654080 | consumed tokens: 9531555840 | elapsed time per iteration (s): 0.20 | learning rate: 1.158E-04 | global batch size: 256 | lm loss: 2.937576E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.878 | TFLOPs: 7.96 | +31: iteration 18190/ 37905 | consumed samples: 4656640 | consumed tokens: 9536798720 | elapsed time per iteration (s): 0.23 | learning rate: 1.157E-04 | global batch size: 256 | lm loss: 2.943844E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.279 | TFLOPs: 7.02 | +31: iteration 18200/ 37905 | consumed samples: 4659200 | consumed tokens: 9542041600 | elapsed time per iteration (s): 0.22 | learning rate: 1.156E-04 | global batch size: 256 | lm loss: 2.977600E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.607 | TFLOPs: 7.42 | +31: iteration 18210/ 37905 | consumed samples: 4661760 | consumed tokens: 9547284480 | elapsed time per iteration (s): 0.21 | learning rate: 1.155E-04 | global batch size: 256 | lm loss: 2.914386E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.985 | TFLOPs: 7.78 | +31: iteration 18220/ 37905 | consumed samples: 4664320 | consumed tokens: 9552527360 | elapsed time per iteration (s): 0.22 | learning rate: 1.155E-04 | global batch size: 256 | lm loss: 2.988902E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.810 | TFLOPs: 7.34 | +31: iteration 18230/ 37905 | consumed samples: 4666880 | consumed tokens: 9557770240 | elapsed time per iteration (s): 0.19 | learning rate: 1.154E-04 | global batch size: 256 | lm loss: 2.936273E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.775 | TFLOPs: 8.49 | +31: iteration 18240/ 37905 | consumed samples: 4669440 | consumed tokens: 9563013120 | elapsed time per iteration (s): 0.21 | learning rate: 1.153E-04 | global batch size: 256 | lm loss: 2.931607E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.084 | TFLOPs: 7.90 | +31: iteration 18250/ 37905 | consumed samples: 4672000 | consumed tokens: 9568256000 | elapsed time per iteration (s): 0.21 | learning rate: 1.152E-04 | global batch size: 256 | lm loss: 2.959596E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.007 | TFLOPs: 7.76 | +31: iteration 18260/ 37905 | consumed samples: 4674560 | consumed tokens: 9573498880 | elapsed time per iteration (s): 0.23 | learning rate: 1.152E-04 | global batch size: 256 | lm loss: 2.910828E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.450 | TFLOPs: 7.10 | +31: iteration 18270/ 37905 | consumed samples: 4677120 | consumed tokens: 9578741760 | elapsed time per iteration (s): 0.23 | learning rate: 1.151E-04 | global batch size: 256 | lm loss: 2.939842E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.822 | TFLOPs: 7.16 | +31: iteration 18280/ 37905 | consumed samples: 4679680 | consumed tokens: 9583984640 | elapsed time per iteration (s): 0.25 | learning rate: 1.150E-04 | global batch size: 256 | lm loss: 2.967379E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.617 | TFLOPs: 6.56 | +31: iteration 18290/ 37905 | consumed samples: 4682240 | consumed tokens: 9589227520 | elapsed time per iteration (s): 0.23 | learning rate: 1.149E-04 | global batch size: 256 | lm loss: 2.951407E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.287 | TFLOPs: 7.03 | +31: iteration 18300/ 37905 | consumed samples: 4684800 | consumed tokens: 9594470400 | elapsed time per iteration (s): 0.24 | learning rate: 1.149E-04 | global batch size: 256 | lm loss: 2.977365E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.099 | TFLOPs: 6.79 | +31: iteration 18310/ 37905 | consumed samples: 4687360 | consumed tokens: 9599713280 | elapsed time per iteration (s): 0.23 | learning rate: 1.148E-04 | global batch size: 256 | lm loss: 2.990677E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.534 | TFLOPs: 7.13 | +31: iteration 18320/ 37905 | consumed samples: 4689920 | consumed tokens: 9604956160 | elapsed time per iteration (s): 0.23 | learning rate: 1.147E-04 | global batch size: 256 | lm loss: 2.928707E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.743 | TFLOPs: 7.17 | +31: iteration 18330/ 37905 | consumed samples: 4692480 | consumed tokens: 9610199040 | elapsed time per iteration (s): 0.21 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 2.957952E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.753 | TFLOPs: 7.90 | +31: iteration 18340/ 37905 | consumed samples: 4695040 | consumed tokens: 9615441920 | elapsed time per iteration (s): 0.21 | learning rate: 1.146E-04 | global batch size: 256 | lm loss: 2.953424E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.212 | TFLOPs: 7.75 | +31: iteration 18350/ 37905 | consumed samples: 4697600 | consumed tokens: 9620684800 | elapsed time per iteration (s): 0.25 | learning rate: 1.145E-04 | global batch size: 256 | lm loss: 2.965253E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1019.299 | TFLOPs: 6.49 | +31: iteration 18360/ 37905 | consumed samples: 4700160 | consumed tokens: 9625927680 | elapsed time per iteration (s): 0.22 | learning rate: 1.144E-04 | global batch size: 256 | lm loss: 2.925530E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.501 | TFLOPs: 7.50 | +31: iteration 18370/ 37905 | consumed samples: 4702720 | consumed tokens: 9631170560 | elapsed time per iteration (s): 0.20 | learning rate: 1.143E-04 | global batch size: 256 | lm loss: 2.990289E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.839 | TFLOPs: 8.05 | +31: iteration 18380/ 37905 | consumed samples: 4705280 | consumed tokens: 9636413440 | elapsed time per iteration (s): 0.25 | learning rate: 1.143E-04 | global batch size: 256 | lm loss: 2.957769E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.289 | TFLOPs: 6.53 | +31: iteration 18390/ 37905 | consumed samples: 4707840 | consumed tokens: 9641656320 | elapsed time per iteration (s): 0.21 | learning rate: 1.142E-04 | global batch size: 256 | lm loss: 2.976048E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.862 | TFLOPs: 7.93 | +31: iteration 18400/ 37905 | consumed samples: 4710400 | consumed tokens: 9646899200 | elapsed time per iteration (s): 0.19 | learning rate: 1.141E-04 | global batch size: 256 | lm loss: 2.949740E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1367.371 | TFLOPs: 8.71 | +31: iteration 18410/ 37905 | consumed samples: 4712960 | consumed tokens: 9652142080 | elapsed time per iteration (s): 0.23 | learning rate: 1.140E-04 | global batch size: 256 | lm loss: 2.920588E+00 | grad norm: 0.282 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.574 | TFLOPs: 7.14 | +31: iteration 18420/ 37905 | consumed samples: 4715520 | consumed tokens: 9657384960 | elapsed time per iteration (s): 0.20 | learning rate: 1.140E-04 | global batch size: 256 | lm loss: 2.952883E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.569 | TFLOPs: 8.12 | +31: iteration 18430/ 37905 | consumed samples: 4718080 | consumed tokens: 9662627840 | elapsed time per iteration (s): 0.25 | learning rate: 1.139E-04 | global batch size: 256 | lm loss: 2.967360E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1027.340 | TFLOPs: 6.54 | +31: iteration 18440/ 37905 | consumed samples: 4720640 | consumed tokens: 9667870720 | elapsed time per iteration (s): 0.24 | learning rate: 1.138E-04 | global batch size: 256 | lm loss: 2.981757E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.272 | TFLOPs: 6.73 | +31: iteration 18450/ 37905 | consumed samples: 4723200 | consumed tokens: 9673113600 | elapsed time per iteration (s): 0.24 | learning rate: 1.137E-04 | global batch size: 256 | lm loss: 2.934364E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.711 | TFLOPs: 6.83 | +31: iteration 18460/ 37905 | consumed samples: 4725760 | consumed tokens: 9678356480 | elapsed time per iteration (s): 0.59 | learning rate: 1.137E-04 | global batch size: 256 | lm loss: 2.927089E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 431.834 | TFLOPs: 2.75 | +31: iteration 18470/ 37905 | consumed samples: 4728320 | consumed tokens: 9683599360 | elapsed time per iteration (s): 0.24 | learning rate: 1.136E-04 | global batch size: 256 | lm loss: 2.942940E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.240 | TFLOPs: 6.68 | +31: iteration 18480/ 37905 | consumed samples: 4730880 | consumed tokens: 9688842240 | elapsed time per iteration (s): 0.36 | learning rate: 1.135E-04 | global batch size: 256 | lm loss: 2.934044E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 715.542 | TFLOPs: 4.56 | +31: iteration 18490/ 37905 | consumed samples: 4733440 | consumed tokens: 9694085120 | elapsed time per iteration (s): 0.24 | learning rate: 1.134E-04 | global batch size: 256 | lm loss: 2.945696E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.917 | TFLOPs: 6.70 | +31: iteration 18500/ 37905 | consumed samples: 4736000 | consumed tokens: 9699328000 | elapsed time per iteration (s): 0.21 | learning rate: 1.134E-04 | global batch size: 256 | lm loss: 2.957911E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.992 | TFLOPs: 7.71 | +31: iteration 18510/ 37905 | consumed samples: 4738560 | consumed tokens: 9704570880 | elapsed time per iteration (s): 0.20 | learning rate: 1.133E-04 | global batch size: 256 | lm loss: 2.950468E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.224 | TFLOPs: 8.19 | +31: iteration 18520/ 37905 | consumed samples: 4741120 | consumed tokens: 9709813760 | elapsed time per iteration (s): 0.23 | learning rate: 1.132E-04 | global batch size: 256 | lm loss: 2.913390E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.736 | TFLOPs: 7.15 | +31: iteration 18530/ 37905 | consumed samples: 4743680 | consumed tokens: 9715056640 | elapsed time per iteration (s): 0.24 | learning rate: 1.132E-04 | global batch size: 256 | lm loss: 2.956347E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.300 | TFLOPs: 6.93 | +31: iteration 18540/ 37905 | consumed samples: 4746240 | consumed tokens: 9720299520 | elapsed time per iteration (s): 0.25 | learning rate: 1.131E-04 | global batch size: 256 | lm loss: 2.964708E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1026.329 | TFLOPs: 6.54 | +31: iteration 18550/ 37905 | consumed samples: 4748800 | consumed tokens: 9725542400 | elapsed time per iteration (s): 0.29 | learning rate: 1.130E-04 | global batch size: 256 | lm loss: 2.966111E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 887.473 | TFLOPs: 5.65 | +31: iteration 18560/ 37905 | consumed samples: 4751360 | consumed tokens: 9730785280 | elapsed time per iteration (s): 0.24 | learning rate: 1.129E-04 | global batch size: 256 | lm loss: 2.965003E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.635 | TFLOPs: 6.70 | +31: iteration 18570/ 37905 | consumed samples: 4753920 | consumed tokens: 9736028160 | elapsed time per iteration (s): 0.23 | learning rate: 1.129E-04 | global batch size: 256 | lm loss: 2.923906E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.949 | TFLOPs: 7.07 | +31: iteration 18580/ 37905 | consumed samples: 4756480 | consumed tokens: 9741271040 | elapsed time per iteration (s): 0.23 | learning rate: 1.128E-04 | global batch size: 256 | lm loss: 2.971823E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.970 | TFLOPs: 7.11 | +31: iteration 18590/ 37905 | consumed samples: 4759040 | consumed tokens: 9746513920 | elapsed time per iteration (s): 0.23 | learning rate: 1.127E-04 | global batch size: 256 | lm loss: 2.935854E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.406 | TFLOPs: 7.00 | +31: iteration 18600/ 37905 | consumed samples: 4761600 | consumed tokens: 9751756800 | elapsed time per iteration (s): 0.23 | learning rate: 1.126E-04 | global batch size: 256 | lm loss: 2.941228E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.694 | TFLOPs: 7.19 | +31: iteration 18610/ 37905 | consumed samples: 4764160 | consumed tokens: 9756999680 | elapsed time per iteration (s): 0.42 | learning rate: 1.126E-04 | global batch size: 256 | lm loss: 2.963451E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 605.607 | TFLOPs: 3.86 | +31: iteration 18620/ 37905 | consumed samples: 4766720 | consumed tokens: 9762242560 | elapsed time per iteration (s): 0.28 | learning rate: 1.125E-04 | global batch size: 256 | lm loss: 2.955050E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 903.619 | TFLOPs: 5.75 | +31: iteration 18630/ 37905 | consumed samples: 4769280 | consumed tokens: 9767485440 | elapsed time per iteration (s): 0.21 | learning rate: 1.124E-04 | global batch size: 256 | lm loss: 2.961352E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.622 | TFLOPs: 7.65 | +31: iteration 18640/ 37905 | consumed samples: 4771840 | consumed tokens: 9772728320 | elapsed time per iteration (s): 0.26 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 2.949999E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1001.848 | TFLOPs: 6.38 | +31: iteration 18650/ 37905 | consumed samples: 4774400 | consumed tokens: 9777971200 | elapsed time per iteration (s): 0.23 | learning rate: 1.123E-04 | global batch size: 256 | lm loss: 2.950579E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.500 | TFLOPs: 6.99 | +31: iteration 18660/ 37905 | consumed samples: 4776960 | consumed tokens: 9783214080 | elapsed time per iteration (s): 0.21 | learning rate: 1.122E-04 | global batch size: 256 | lm loss: 2.975917E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.454 | TFLOPs: 7.61 | +31: iteration 18670/ 37905 | consumed samples: 4779520 | consumed tokens: 9788456960 | elapsed time per iteration (s): 0.22 | learning rate: 1.121E-04 | global batch size: 256 | lm loss: 2.930199E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.114 | TFLOPs: 7.37 | +31: iteration 18680/ 37905 | consumed samples: 4782080 | consumed tokens: 9793699840 | elapsed time per iteration (s): 0.23 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 3.009149E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.793 | TFLOPs: 7.04 | +31: iteration 18690/ 37905 | consumed samples: 4784640 | consumed tokens: 9798942720 | elapsed time per iteration (s): 0.20 | learning rate: 1.120E-04 | global batch size: 256 | lm loss: 2.947421E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.426 | TFLOPs: 8.05 | +31: iteration 18700/ 37905 | consumed samples: 4787200 | consumed tokens: 9804185600 | elapsed time per iteration (s): 0.24 | learning rate: 1.119E-04 | global batch size: 256 | lm loss: 2.960779E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.461 | TFLOPs: 6.77 | +31: iteration 18710/ 37905 | consumed samples: 4789760 | consumed tokens: 9809428480 | elapsed time per iteration (s): 0.24 | learning rate: 1.118E-04 | global batch size: 256 | lm loss: 2.967583E+00 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.474 | TFLOPs: 6.84 | +31: iteration 18720/ 37905 | consumed samples: 4792320 | consumed tokens: 9814671360 | elapsed time per iteration (s): 0.33 | learning rate: 1.117E-04 | global batch size: 256 | lm loss: 2.957696E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 774.334 | TFLOPs: 4.93 | +31: iteration 18730/ 37905 | consumed samples: 4794880 | consumed tokens: 9819914240 | elapsed time per iteration (s): 0.23 | learning rate: 1.117E-04 | global batch size: 256 | lm loss: 2.949000E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.487 | TFLOPs: 7.12 | +31: iteration 18740/ 37905 | consumed samples: 4797440 | consumed tokens: 9825157120 | elapsed time per iteration (s): 0.23 | learning rate: 1.116E-04 | global batch size: 256 | lm loss: 2.961351E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.893 | TFLOPs: 6.99 | +31: iteration 18750/ 37905 | consumed samples: 4800000 | consumed tokens: 9830400000 | elapsed time per iteration (s): 0.21 | learning rate: 1.115E-04 | global batch size: 256 | lm loss: 2.949372E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.830 | TFLOPs: 7.78 | +31: iteration 18760/ 37905 | consumed samples: 4802560 | consumed tokens: 9835642880 | elapsed time per iteration (s): 0.27 | learning rate: 1.114E-04 | global batch size: 256 | lm loss: 2.977421E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 953.990 | TFLOPs: 6.08 | +31: iteration 18770/ 37905 | consumed samples: 4805120 | consumed tokens: 9840885760 | elapsed time per iteration (s): 0.23 | learning rate: 1.114E-04 | global batch size: 256 | lm loss: 2.907962E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.205 | TFLOPs: 7.01 | +31: iteration 18780/ 37905 | consumed samples: 4807680 | consumed tokens: 9846128640 | elapsed time per iteration (s): 0.21 | learning rate: 1.113E-04 | global batch size: 256 | lm loss: 2.976626E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.468 | TFLOPs: 7.83 | +31: iteration 18790/ 37905 | consumed samples: 4810240 | consumed tokens: 9851371520 | elapsed time per iteration (s): 0.35 | learning rate: 1.112E-04 | global batch size: 256 | lm loss: 2.951406E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 723.061 | TFLOPs: 4.61 | +31: iteration 18800/ 37905 | consumed samples: 4812800 | consumed tokens: 9856614400 | elapsed time per iteration (s): 0.21 | learning rate: 1.111E-04 | global batch size: 256 | lm loss: 2.957250E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.733 | TFLOPs: 7.95 | +31: iteration 18810/ 37905 | consumed samples: 4815360 | consumed tokens: 9861857280 | elapsed time per iteration (s): 0.22 | learning rate: 1.111E-04 | global batch size: 256 | lm loss: 2.910613E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.613 | TFLOPs: 7.43 | +31: iteration 18820/ 37905 | consumed samples: 4817920 | consumed tokens: 9867100160 | elapsed time per iteration (s): 0.27 | learning rate: 1.110E-04 | global batch size: 256 | lm loss: 2.970064E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 943.761 | TFLOPs: 6.01 | +31: iteration 18830/ 37905 | consumed samples: 4820480 | consumed tokens: 9872343040 | elapsed time per iteration (s): 0.22 | learning rate: 1.109E-04 | global batch size: 256 | lm loss: 2.958374E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.031 | TFLOPs: 7.35 | +31: iteration 18840/ 37905 | consumed samples: 4823040 | consumed tokens: 9877585920 | elapsed time per iteration (s): 0.22 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 2.915676E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.553 | TFLOPs: 7.43 | +31: iteration 18850/ 37905 | consumed samples: 4825600 | consumed tokens: 9882828800 | elapsed time per iteration (s): 0.22 | learning rate: 1.108E-04 | global batch size: 256 | lm loss: 2.954730E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.189 | TFLOPs: 7.31 | +31: iteration 18860/ 37905 | consumed samples: 4828160 | consumed tokens: 9888071680 | elapsed time per iteration (s): 0.30 | learning rate: 1.107E-04 | global batch size: 256 | lm loss: 2.948260E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 860.990 | TFLOPs: 5.48 | +31: iteration 18870/ 37905 | consumed samples: 4830720 | consumed tokens: 9893314560 | elapsed time per iteration (s): 0.23 | learning rate: 1.106E-04 | global batch size: 256 | lm loss: 2.956077E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.677 | TFLOPs: 7.12 | +31: iteration 18880/ 37905 | consumed samples: 4833280 | consumed tokens: 9898557440 | elapsed time per iteration (s): 0.26 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 2.949617E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 971.599 | TFLOPs: 6.19 | +31: iteration 18890/ 37905 | consumed samples: 4835840 | consumed tokens: 9903800320 | elapsed time per iteration (s): 0.22 | learning rate: 1.105E-04 | global batch size: 256 | lm loss: 2.974713E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.526 | TFLOPs: 7.25 | +31: iteration 18900/ 37905 | consumed samples: 4838400 | consumed tokens: 9909043200 | elapsed time per iteration (s): 0.22 | learning rate: 1.104E-04 | global batch size: 256 | lm loss: 2.936911E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.162 | TFLOPs: 7.33 | +31: iteration 18910/ 37905 | consumed samples: 4840960 | consumed tokens: 9914286080 | elapsed time per iteration (s): 0.27 | learning rate: 1.103E-04 | global batch size: 256 | lm loss: 2.951233E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 965.461 | TFLOPs: 6.15 | +31: iteration 18920/ 37905 | consumed samples: 4843520 | consumed tokens: 9919528960 | elapsed time per iteration (s): 0.25 | learning rate: 1.102E-04 | global batch size: 256 | lm loss: 2.926867E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1010.543 | TFLOPs: 6.44 | +31: iteration 18930/ 37905 | consumed samples: 4846080 | consumed tokens: 9924771840 | elapsed time per iteration (s): 0.26 | learning rate: 1.102E-04 | global batch size: 256 | lm loss: 2.941034E+00 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 972.629 | TFLOPs: 6.19 | +31: iteration 18940/ 37905 | consumed samples: 4848640 | consumed tokens: 9930014720 | elapsed time per iteration (s): 0.19 | learning rate: 1.101E-04 | global batch size: 256 | lm loss: 2.989863E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.250 | TFLOPs: 8.55 | +31: iteration 18950/ 37905 | consumed samples: 4851200 | consumed tokens: 9935257600 | elapsed time per iteration (s): 0.24 | learning rate: 1.100E-04 | global batch size: 256 | lm loss: 2.943569E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.737 | TFLOPs: 6.87 | +31: iteration 18960/ 37905 | consumed samples: 4853760 | consumed tokens: 9940500480 | elapsed time per iteration (s): 0.20 | learning rate: 1.099E-04 | global batch size: 256 | lm loss: 2.913574E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.595 | TFLOPs: 8.02 | +31: iteration 18970/ 37905 | consumed samples: 4856320 | consumed tokens: 9945743360 | elapsed time per iteration (s): 0.21 | learning rate: 1.099E-04 | global batch size: 256 | lm loss: 2.973420E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.146 | TFLOPs: 7.94 | +31: iteration 18980/ 37905 | consumed samples: 4858880 | consumed tokens: 9950986240 | elapsed time per iteration (s): 0.21 | learning rate: 1.098E-04 | global batch size: 256 | lm loss: 2.975124E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.347 | TFLOPs: 7.87 | +31: iteration 18990/ 37905 | consumed samples: 4861440 | consumed tokens: 9956229120 | elapsed time per iteration (s): 0.23 | learning rate: 1.097E-04 | global batch size: 256 | lm loss: 2.961456E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.294 | TFLOPs: 7.16 | +31: iteration 19000/ 37905 | consumed samples: 4864000 | consumed tokens: 9961472000 | elapsed time per iteration (s): 0.24 | learning rate: 1.096E-04 | global batch size: 256 | lm loss: 2.978700E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.183 | TFLOPs: 6.90 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 19000 | lm loss value: 2.837207E+00 | lm loss PPL: 1.706803E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 19000 to checkpoints_83m + 0: [2022-11-24 15:19:32,549] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step19000 is begin to save! + 0: [2022-11-24 15:19:32,594] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,830] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,831] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,842] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,843] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,854] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,854] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,865] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,888] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,899] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,911] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,922] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,945] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:19:32,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:19:32,947] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step19000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:19:32,947] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:19:32,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,018] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:19:33,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:19:33,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:19:33,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:19:33,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:19:33,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +16: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +24: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:19:33,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:19:33,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +24: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +24: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +25: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:19:33,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 4: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:19:33,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 4: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +21: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +17: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:19:33,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +21: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 7: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:19:33,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +20: [2022-11-24 15:19:33,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:19:33,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:19:33,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 7: [2022-11-24 15:19:33,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:19:33,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 4: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:19:33,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +16: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +20: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:19:33,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:19:33,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +21: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:19:33,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:19:33,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +11: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +11: [2022-11-24 15:19:33,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 15:19:33,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:19:33,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:19:33,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:19:33,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:19:33,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 7: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 4: [2022-11-24 15:19:33,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:19:33,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:19:33,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +20: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +24: [2022-11-24 15:19:33,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +16: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:19:33,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:19:33,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +14: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +21: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:19:33,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +11: [2022-11-24 15:19:33,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:19:33,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:19:33,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:19:33,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 7: [2022-11-24 15:19:33,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +17: [2022-11-24 15:19:33,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:19:33,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:19:33,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:19:33,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 4: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +16: [2022-11-24 15:19:33,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +24: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:19:33,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +20: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:19:33,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:19:33,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:19:33,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:19:33,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +21: [2022-11-24 15:19:33,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +11: [2022-11-24 15:19:33,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:19:33,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,051] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,051] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,051] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,051] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,051] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 15:19:33,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:19:33,052] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,053] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:19:33,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 7: [2022-11-24 15:19:33,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,054] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 15:19:33,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:19:33,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +20: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +16: [2022-11-24 15:19:33,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +24: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:19:33,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:19:33,055] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +27: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +27: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +10: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +27: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +10: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +27: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,056] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,056] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +26: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +26: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,057] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +26: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +31: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 3: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +31: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +31: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +31: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:19:33,057] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +13: [2022-11-24 15:19:33,058] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +28: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +10: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +21: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +27: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +27: [2022-11-24 15:19:33,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +31: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:19:33,059] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,059] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 3: [2022-11-24 15:19:33,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,060] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:19:33,060] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:19:33,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:19:33,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 7: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 4: [2022-11-24 15:19:33,061] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:19:33,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +20: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +20: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +24: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:19:33,062] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +16: [2022-11-24 15:19:33,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:19:33,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:19:33,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +30: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:19:33,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:19:33,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,063] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +21: [2022-11-24 15:19:33,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,064] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +14: [2022-11-24 15:19:33,064] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,064] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:19:33,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +11: [2022-11-24 15:19:33,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,065] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:19:33,065] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +27: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,065] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,065] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,065] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:19:33,065] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +10: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:19:33,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +12: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,066] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 7: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,066] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +16: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +19: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +30: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +19: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 1: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 4: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +18: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +22: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +25: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +22: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 9: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 6: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +31: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +27: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +31: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,067] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +20: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,067] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,068] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +13: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,068] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +26: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +13: [2022-11-24 15:19:33,068] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +20: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,068] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,068] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +31: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,068] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:19:33,068] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +10: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:19:33,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 3: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:19:33,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 5: [2022-11-24 15:19:33,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 8: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:19:33,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +17: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +23: [2022-11-24 15:19:33,069] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +27: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +10: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +12: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +31: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +10: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +14: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +20: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +18: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +28: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +13: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +28: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +13: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +20: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 2: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 3: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +26: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +29: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +11: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +29: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 3: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +18: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +18: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:19:33,070] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,070] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! +15: [2022-11-24 15:19:33,071] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:19:33,071] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step19000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:19:33,071] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step19000 is ready now! + 0: successfully saved checkpoint at iteration 19000 to checkpoints_83m +31: time (ms) | save-checkpoint: 585.53 +31: iteration 19010/ 37905 | consumed samples: 4866560 | consumed tokens: 9966714880 | elapsed time per iteration (s): 0.25 | learning rate: 1.096E-04 | global batch size: 256 | lm loss: 2.978187E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1007.586 | TFLOPs: 6.42 | +31: iteration 19020/ 37905 | consumed samples: 4869120 | consumed tokens: 9971957760 | elapsed time per iteration (s): 0.24 | learning rate: 1.095E-04 | global batch size: 256 | lm loss: 2.969422E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.741 | TFLOPs: 6.93 | +31: iteration 19030/ 37905 | consumed samples: 4871680 | consumed tokens: 9977200640 | elapsed time per iteration (s): 0.22 | learning rate: 1.094E-04 | global batch size: 256 | lm loss: 2.935714E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.866 | TFLOPs: 7.27 | +31: iteration 19040/ 37905 | consumed samples: 4874240 | consumed tokens: 9982443520 | elapsed time per iteration (s): 0.20 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 2.971617E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1302.319 | TFLOPs: 8.29 | +31: iteration 19050/ 37905 | consumed samples: 4876800 | consumed tokens: 9987686400 | elapsed time per iteration (s): 0.23 | learning rate: 1.093E-04 | global batch size: 256 | lm loss: 2.931518E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.083 | TFLOPs: 7.20 | +31: iteration 19060/ 37905 | consumed samples: 4879360 | consumed tokens: 9992929280 | elapsed time per iteration (s): 0.23 | learning rate: 1.092E-04 | global batch size: 256 | lm loss: 2.937475E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.994 | TFLOPs: 7.05 | +31: iteration 19070/ 37905 | consumed samples: 4881920 | consumed tokens: 9998172160 | elapsed time per iteration (s): 0.20 | learning rate: 1.091E-04 | global batch size: 256 | lm loss: 2.924624E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.713 | TFLOPs: 8.12 | +31: iteration 19080/ 37905 | consumed samples: 4884480 | consumed tokens: 10003415040 | elapsed time per iteration (s): 0.24 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 2.960176E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.164 | TFLOPs: 6.93 | +31: iteration 19090/ 37905 | consumed samples: 4887040 | consumed tokens: 10008657920 | elapsed time per iteration (s): 0.21 | learning rate: 1.090E-04 | global batch size: 256 | lm loss: 2.975311E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.041 | TFLOPs: 7.92 | +31: iteration 19100/ 37905 | consumed samples: 4889600 | consumed tokens: 10013900800 | elapsed time per iteration (s): 0.23 | learning rate: 1.089E-04 | global batch size: 256 | lm loss: 2.983877E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.951 | TFLOPs: 7.00 | +31: iteration 19110/ 37905 | consumed samples: 4892160 | consumed tokens: 10019143680 | elapsed time per iteration (s): 0.23 | learning rate: 1.088E-04 | global batch size: 256 | lm loss: 2.983385E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.699 | TFLOPs: 7.21 | +31: iteration 19120/ 37905 | consumed samples: 4894720 | consumed tokens: 10024386560 | elapsed time per iteration (s): 0.21 | learning rate: 1.088E-04 | global batch size: 256 | lm loss: 2.944458E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.571 | TFLOPs: 7.94 | +31: iteration 19130/ 37905 | consumed samples: 4897280 | consumed tokens: 10029629440 | elapsed time per iteration (s): 0.21 | learning rate: 1.087E-04 | global batch size: 256 | lm loss: 2.940230E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.345 | TFLOPs: 7.63 | +31: iteration 19140/ 37905 | consumed samples: 4899840 | consumed tokens: 10034872320 | elapsed time per iteration (s): 0.23 | learning rate: 1.086E-04 | global batch size: 256 | lm loss: 2.944090E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.421 | TFLOPs: 7.22 | +31: iteration 19150/ 37905 | consumed samples: 4902400 | consumed tokens: 10040115200 | elapsed time per iteration (s): 0.23 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 2.932680E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.456 | TFLOPs: 7.21 | +31: iteration 19160/ 37905 | consumed samples: 4904960 | consumed tokens: 10045358080 | elapsed time per iteration (s): 0.21 | learning rate: 1.085E-04 | global batch size: 256 | lm loss: 2.961805E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.829 | TFLOPs: 7.86 | +31: iteration 19170/ 37905 | consumed samples: 4907520 | consumed tokens: 10050600960 | elapsed time per iteration (s): 0.21 | learning rate: 1.084E-04 | global batch size: 256 | lm loss: 2.937078E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.665 | TFLOPs: 7.89 | +31: iteration 19180/ 37905 | consumed samples: 4910080 | consumed tokens: 10055843840 | elapsed time per iteration (s): 0.26 | learning rate: 1.083E-04 | global batch size: 256 | lm loss: 2.958242E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 985.030 | TFLOPs: 6.27 | +31: iteration 19190/ 37905 | consumed samples: 4912640 | consumed tokens: 10061086720 | elapsed time per iteration (s): 0.21 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 2.956841E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.318 | TFLOPs: 7.92 | +31: iteration 19200/ 37905 | consumed samples: 4915200 | consumed tokens: 10066329600 | elapsed time per iteration (s): 0.23 | learning rate: 1.082E-04 | global batch size: 256 | lm loss: 2.955980E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.032 | TFLOPs: 7.08 | +31: iteration 19210/ 37905 | consumed samples: 4917760 | consumed tokens: 10071572480 | elapsed time per iteration (s): 0.23 | learning rate: 1.081E-04 | global batch size: 256 | lm loss: 2.947349E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.897 | TFLOPs: 7.21 | +31: iteration 19220/ 37905 | consumed samples: 4920320 | consumed tokens: 10076815360 | elapsed time per iteration (s): 0.23 | learning rate: 1.080E-04 | global batch size: 256 | lm loss: 2.952515E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.374 | TFLOPs: 7.00 | +31: iteration 19230/ 37905 | consumed samples: 4922880 | consumed tokens: 10082058240 | elapsed time per iteration (s): 0.24 | learning rate: 1.079E-04 | global batch size: 256 | lm loss: 2.949360E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.805 | TFLOPs: 6.74 | +31: iteration 19240/ 37905 | consumed samples: 4925440 | consumed tokens: 10087301120 | elapsed time per iteration (s): 0.23 | learning rate: 1.079E-04 | global batch size: 256 | lm loss: 2.951797E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.243 | TFLOPs: 7.12 | +31: iteration 19250/ 37905 | consumed samples: 4928000 | consumed tokens: 10092544000 | elapsed time per iteration (s): 0.22 | learning rate: 1.078E-04 | global batch size: 256 | lm loss: 2.981716E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.319 | TFLOPs: 7.57 | +31: iteration 19260/ 37905 | consumed samples: 4930560 | consumed tokens: 10097786880 | elapsed time per iteration (s): 0.23 | learning rate: 1.077E-04 | global batch size: 256 | lm loss: 2.939577E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.317 | TFLOPs: 7.01 | +31: iteration 19270/ 37905 | consumed samples: 4933120 | consumed tokens: 10103029760 | elapsed time per iteration (s): 0.23 | learning rate: 1.076E-04 | global batch size: 256 | lm loss: 2.919529E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.921 | TFLOPs: 7.12 | +31: iteration 19280/ 37905 | consumed samples: 4935680 | consumed tokens: 10108272640 | elapsed time per iteration (s): 0.23 | learning rate: 1.076E-04 | global batch size: 256 | lm loss: 2.944967E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.522 | TFLOPs: 7.02 | +31: iteration 19290/ 37905 | consumed samples: 4938240 | consumed tokens: 10113515520 | elapsed time per iteration (s): 0.22 | learning rate: 1.075E-04 | global batch size: 256 | lm loss: 2.961437E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.336 | TFLOPs: 7.48 | +31: iteration 19300/ 37905 | consumed samples: 4940800 | consumed tokens: 10118758400 | elapsed time per iteration (s): 0.24 | learning rate: 1.074E-04 | global batch size: 256 | lm loss: 2.950163E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.023 | TFLOPs: 6.93 | +31: iteration 19310/ 37905 | consumed samples: 4943360 | consumed tokens: 10124001280 | elapsed time per iteration (s): 0.21 | learning rate: 1.073E-04 | global batch size: 256 | lm loss: 2.943117E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.311 | TFLOPs: 7.90 | +31: iteration 19320/ 37905 | consumed samples: 4945920 | consumed tokens: 10129244160 | elapsed time per iteration (s): 0.20 | learning rate: 1.073E-04 | global batch size: 256 | lm loss: 2.926016E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.741 | TFLOPs: 8.31 | +31: iteration 19330/ 37905 | consumed samples: 4948480 | consumed tokens: 10134487040 | elapsed time per iteration (s): 0.22 | learning rate: 1.072E-04 | global batch size: 256 | lm loss: 2.919755E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.059 | TFLOPs: 7.48 | +31: iteration 19340/ 37905 | consumed samples: 4951040 | consumed tokens: 10139729920 | elapsed time per iteration (s): 0.24 | learning rate: 1.071E-04 | global batch size: 256 | lm loss: 2.953634E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.579 | TFLOPs: 6.88 | +31: iteration 19350/ 37905 | consumed samples: 4953600 | consumed tokens: 10144972800 | elapsed time per iteration (s): 0.23 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 2.942576E+00 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.749 | TFLOPs: 6.99 | +31: iteration 19360/ 37905 | consumed samples: 4956160 | consumed tokens: 10150215680 | elapsed time per iteration (s): 0.24 | learning rate: 1.070E-04 | global batch size: 256 | lm loss: 2.940884E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.140 | TFLOPs: 6.93 | +31: iteration 19370/ 37905 | consumed samples: 4958720 | consumed tokens: 10155458560 | elapsed time per iteration (s): 0.23 | learning rate: 1.069E-04 | global batch size: 256 | lm loss: 2.938452E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.967 | TFLOPs: 7.20 | +31: iteration 19380/ 37905 | consumed samples: 4961280 | consumed tokens: 10160701440 | elapsed time per iteration (s): 0.23 | learning rate: 1.068E-04 | global batch size: 256 | lm loss: 2.915395E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.212 | TFLOPs: 6.96 | +31: iteration 19390/ 37905 | consumed samples: 4963840 | consumed tokens: 10165944320 | elapsed time per iteration (s): 0.23 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 2.948950E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.860 | TFLOPs: 7.20 | +31: iteration 19400/ 37905 | consumed samples: 4966400 | consumed tokens: 10171187200 | elapsed time per iteration (s): 0.24 | learning rate: 1.067E-04 | global batch size: 256 | lm loss: 2.949183E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.905 | TFLOPs: 6.69 | +31: iteration 19410/ 37905 | consumed samples: 4968960 | consumed tokens: 10176430080 | elapsed time per iteration (s): 0.20 | learning rate: 1.066E-04 | global batch size: 256 | lm loss: 2.955969E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1262.621 | TFLOPs: 8.04 | +31: iteration 19420/ 37905 | consumed samples: 4971520 | consumed tokens: 10181672960 | elapsed time per iteration (s): 0.23 | learning rate: 1.065E-04 | global batch size: 256 | lm loss: 2.959571E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.180 | TFLOPs: 6.94 | +31: iteration 19430/ 37905 | consumed samples: 4974080 | consumed tokens: 10186915840 | elapsed time per iteration (s): 0.24 | learning rate: 1.064E-04 | global batch size: 256 | lm loss: 2.976624E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.684 | TFLOPs: 6.84 | +31: iteration 19440/ 37905 | consumed samples: 4976640 | consumed tokens: 10192158720 | elapsed time per iteration (s): 0.22 | learning rate: 1.064E-04 | global batch size: 256 | lm loss: 2.952502E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.117 | TFLOPs: 7.40 | +31: iteration 19450/ 37905 | consumed samples: 4979200 | consumed tokens: 10197401600 | elapsed time per iteration (s): 0.23 | learning rate: 1.063E-04 | global batch size: 256 | lm loss: 2.966639E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.991 | TFLOPs: 7.20 | +31: iteration 19460/ 37905 | consumed samples: 4981760 | consumed tokens: 10202644480 | elapsed time per iteration (s): 0.23 | learning rate: 1.062E-04 | global batch size: 256 | lm loss: 2.937896E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.142 | TFLOPs: 7.08 | +31: iteration 19470/ 37905 | consumed samples: 4984320 | consumed tokens: 10207887360 | elapsed time per iteration (s): 0.23 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 2.924743E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.652 | TFLOPs: 7.19 | +31: iteration 19480/ 37905 | consumed samples: 4986880 | consumed tokens: 10213130240 | elapsed time per iteration (s): 0.25 | learning rate: 1.061E-04 | global batch size: 256 | lm loss: 2.929379E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.583 | TFLOPs: 6.44 | +31: iteration 19490/ 37905 | consumed samples: 4989440 | consumed tokens: 10218373120 | elapsed time per iteration (s): 0.25 | learning rate: 1.060E-04 | global batch size: 256 | lm loss: 2.952458E+00 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.673 | TFLOPs: 6.60 | +31: iteration 19500/ 37905 | consumed samples: 4992000 | consumed tokens: 10223616000 | elapsed time per iteration (s): 0.22 | learning rate: 1.059E-04 | global batch size: 256 | lm loss: 2.931986E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.479 | TFLOPs: 7.41 | +31: iteration 19510/ 37905 | consumed samples: 4994560 | consumed tokens: 10228858880 | elapsed time per iteration (s): 0.25 | learning rate: 1.058E-04 | global batch size: 256 | lm loss: 2.964995E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.967 | TFLOPs: 6.50 | +31: iteration 19520/ 37905 | consumed samples: 4997120 | consumed tokens: 10234101760 | elapsed time per iteration (s): 0.22 | learning rate: 1.058E-04 | global batch size: 256 | lm loss: 2.962109E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.564 | TFLOPs: 7.29 | +31: iteration 19530/ 37905 | consumed samples: 4999680 | consumed tokens: 10239344640 | elapsed time per iteration (s): 0.24 | learning rate: 1.057E-04 | global batch size: 256 | lm loss: 2.925484E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.571 | TFLOPs: 6.82 | +31: iteration 19540/ 37905 | consumed samples: 5002240 | consumed tokens: 10244587520 | elapsed time per iteration (s): 0.23 | learning rate: 1.056E-04 | global batch size: 256 | lm loss: 2.956987E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.146 | TFLOPs: 6.96 | +31: iteration 19550/ 37905 | consumed samples: 5004800 | consumed tokens: 10249830400 | elapsed time per iteration (s): 0.22 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 2.979369E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.529 | TFLOPs: 7.56 | +31: iteration 19560/ 37905 | consumed samples: 5007360 | consumed tokens: 10255073280 | elapsed time per iteration (s): 0.22 | learning rate: 1.055E-04 | global batch size: 256 | lm loss: 2.936363E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.268 | TFLOPs: 7.29 | +31: iteration 19570/ 37905 | consumed samples: 5009920 | consumed tokens: 10260316160 | elapsed time per iteration (s): 0.21 | learning rate: 1.054E-04 | global batch size: 256 | lm loss: 2.926488E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.658 | TFLOPs: 7.86 | +31: iteration 19580/ 37905 | consumed samples: 5012480 | consumed tokens: 10265559040 | elapsed time per iteration (s): 0.26 | learning rate: 1.053E-04 | global batch size: 256 | lm loss: 2.953671E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.189 | TFLOPs: 6.34 | +31: iteration 19590/ 37905 | consumed samples: 5015040 | consumed tokens: 10270801920 | elapsed time per iteration (s): 0.24 | learning rate: 1.052E-04 | global batch size: 256 | lm loss: 2.917384E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.052 | TFLOPs: 6.91 | +31: iteration 19600/ 37905 | consumed samples: 5017600 | consumed tokens: 10276044800 | elapsed time per iteration (s): 0.20 | learning rate: 1.052E-04 | global batch size: 256 | lm loss: 2.917069E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1291.313 | TFLOPs: 8.22 | +31: iteration 19610/ 37905 | consumed samples: 5020160 | consumed tokens: 10281287680 | elapsed time per iteration (s): 0.21 | learning rate: 1.051E-04 | global batch size: 256 | lm loss: 2.953076E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.863 | TFLOPs: 7.88 | +31: iteration 19620/ 37905 | consumed samples: 5022720 | consumed tokens: 10286530560 | elapsed time per iteration (s): 0.22 | learning rate: 1.050E-04 | global batch size: 256 | lm loss: 2.965328E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.018 | TFLOPs: 7.57 | +31: iteration 19630/ 37905 | consumed samples: 5025280 | consumed tokens: 10291773440 | elapsed time per iteration (s): 0.28 | learning rate: 1.049E-04 | global batch size: 256 | lm loss: 2.966591E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 929.684 | TFLOPs: 5.92 | +31: iteration 19640/ 37905 | consumed samples: 5027840 | consumed tokens: 10297016320 | elapsed time per iteration (s): 0.24 | learning rate: 1.049E-04 | global batch size: 256 | lm loss: 2.973726E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.904 | TFLOPs: 6.78 | +31: iteration 19650/ 37905 | consumed samples: 5030400 | consumed tokens: 10302259200 | elapsed time per iteration (s): 0.23 | learning rate: 1.048E-04 | global batch size: 256 | lm loss: 2.913275E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1136.822 | TFLOPs: 7.24 | +31: iteration 19660/ 37905 | consumed samples: 5032960 | consumed tokens: 10307502080 | elapsed time per iteration (s): 0.23 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 2.948754E+00 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.349 | TFLOPs: 6.97 | +31: iteration 19670/ 37905 | consumed samples: 5035520 | consumed tokens: 10312744960 | elapsed time per iteration (s): 0.22 | learning rate: 1.047E-04 | global batch size: 256 | lm loss: 2.929175E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.713 | TFLOPs: 7.41 | +31: iteration 19680/ 37905 | consumed samples: 5038080 | consumed tokens: 10317987840 | elapsed time per iteration (s): 0.23 | learning rate: 1.046E-04 | global batch size: 256 | lm loss: 2.919651E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.028 | TFLOPs: 7.17 | +31: iteration 19690/ 37905 | consumed samples: 5040640 | consumed tokens: 10323230720 | elapsed time per iteration (s): 0.24 | learning rate: 1.045E-04 | global batch size: 256 | lm loss: 2.935018E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.649 | TFLOPs: 6.89 | +31: iteration 19700/ 37905 | consumed samples: 5043200 | consumed tokens: 10328473600 | elapsed time per iteration (s): 0.21 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 2.935179E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.981 | TFLOPs: 7.59 | +31: iteration 19710/ 37905 | consumed samples: 5045760 | consumed tokens: 10333716480 | elapsed time per iteration (s): 0.21 | learning rate: 1.044E-04 | global batch size: 256 | lm loss: 2.927916E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.686 | TFLOPs: 7.72 | +31: iteration 19720/ 37905 | consumed samples: 5048320 | consumed tokens: 10338959360 | elapsed time per iteration (s): 0.21 | learning rate: 1.043E-04 | global batch size: 256 | lm loss: 2.914538E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.461 | TFLOPs: 7.76 | +31: iteration 19730/ 37905 | consumed samples: 5050880 | consumed tokens: 10344202240 | elapsed time per iteration (s): 0.21 | learning rate: 1.042E-04 | global batch size: 256 | lm loss: 2.936959E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.948 | TFLOPs: 7.80 | +31: iteration 19740/ 37905 | consumed samples: 5053440 | consumed tokens: 10349445120 | elapsed time per iteration (s): 0.19 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 2.971894E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1343.430 | TFLOPs: 8.56 | +31: iteration 19750/ 37905 | consumed samples: 5056000 | consumed tokens: 10354688000 | elapsed time per iteration (s): 0.51 | learning rate: 1.041E-04 | global batch size: 256 | lm loss: 2.943528E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 505.273 | TFLOPs: 3.22 | +31: iteration 19760/ 37905 | consumed samples: 5058560 | consumed tokens: 10359930880 | elapsed time per iteration (s): 0.25 | learning rate: 1.040E-04 | global batch size: 256 | lm loss: 2.936587E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.225 | TFLOPs: 6.43 | +31: iteration 19770/ 37905 | consumed samples: 5061120 | consumed tokens: 10365173760 | elapsed time per iteration (s): 0.24 | learning rate: 1.039E-04 | global batch size: 256 | lm loss: 2.946098E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.185 | TFLOPs: 6.69 | +31: iteration 19780/ 37905 | consumed samples: 5063680 | consumed tokens: 10370416640 | elapsed time per iteration (s): 0.22 | learning rate: 1.038E-04 | global batch size: 256 | lm loss: 2.952415E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.595 | TFLOPs: 7.30 | +31: iteration 19790/ 37905 | consumed samples: 5066240 | consumed tokens: 10375659520 | elapsed time per iteration (s): 0.22 | learning rate: 1.038E-04 | global batch size: 256 | lm loss: 2.947210E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.060 | TFLOPs: 7.39 | +31: iteration 19800/ 37905 | consumed samples: 5068800 | consumed tokens: 10380902400 | elapsed time per iteration (s): 0.25 | learning rate: 1.037E-04 | global batch size: 256 | lm loss: 2.914025E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1015.635 | TFLOPs: 6.47 | +31: iteration 19810/ 37905 | consumed samples: 5071360 | consumed tokens: 10386145280 | elapsed time per iteration (s): 0.21 | learning rate: 1.036E-04 | global batch size: 256 | lm loss: 2.951207E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.939 | TFLOPs: 7.65 | +31: iteration 19820/ 37905 | consumed samples: 5073920 | consumed tokens: 10391388160 | elapsed time per iteration (s): 0.21 | learning rate: 1.035E-04 | global batch size: 256 | lm loss: 2.943768E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.435 | TFLOPs: 7.92 | +31: iteration 19830/ 37905 | consumed samples: 5076480 | consumed tokens: 10396631040 | elapsed time per iteration (s): 0.25 | learning rate: 1.035E-04 | global batch size: 256 | lm loss: 2.913826E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1019.722 | TFLOPs: 6.49 | +31: iteration 19840/ 37905 | consumed samples: 5079040 | consumed tokens: 10401873920 | elapsed time per iteration (s): 0.21 | learning rate: 1.034E-04 | global batch size: 256 | lm loss: 2.918534E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.104 | TFLOPs: 7.78 | +31: iteration 19850/ 37905 | consumed samples: 5081600 | consumed tokens: 10407116800 | elapsed time per iteration (s): 0.23 | learning rate: 1.033E-04 | global batch size: 256 | lm loss: 2.966926E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.365 | TFLOPs: 7.08 | +31: iteration 19860/ 37905 | consumed samples: 5084160 | consumed tokens: 10412359680 | elapsed time per iteration (s): 0.19 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 2.960005E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1318.052 | TFLOPs: 8.39 | +31: iteration 19870/ 37905 | consumed samples: 5086720 | consumed tokens: 10417602560 | elapsed time per iteration (s): 0.25 | learning rate: 1.032E-04 | global batch size: 256 | lm loss: 2.974193E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.952 | TFLOPs: 6.60 | +31: iteration 19880/ 37905 | consumed samples: 5089280 | consumed tokens: 10422845440 | elapsed time per iteration (s): 0.25 | learning rate: 1.031E-04 | global batch size: 256 | lm loss: 2.945497E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.299 | TFLOPs: 6.51 | +31: iteration 19890/ 37905 | consumed samples: 5091840 | consumed tokens: 10428088320 | elapsed time per iteration (s): 0.20 | learning rate: 1.030E-04 | global batch size: 256 | lm loss: 2.948804E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.886 | TFLOPs: 8.33 | +31: iteration 19900/ 37905 | consumed samples: 5094400 | consumed tokens: 10433331200 | elapsed time per iteration (s): 0.20 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 2.939389E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1257.059 | TFLOPs: 8.01 | +31: iteration 19910/ 37905 | consumed samples: 5096960 | consumed tokens: 10438574080 | elapsed time per iteration (s): 0.25 | learning rate: 1.029E-04 | global batch size: 256 | lm loss: 2.964807E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.256 | TFLOPs: 6.64 | +31: iteration 19920/ 37905 | consumed samples: 5099520 | consumed tokens: 10443816960 | elapsed time per iteration (s): 0.21 | learning rate: 1.028E-04 | global batch size: 256 | lm loss: 2.978580E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.369 | TFLOPs: 7.62 | +31: iteration 19930/ 37905 | consumed samples: 5102080 | consumed tokens: 10449059840 | elapsed time per iteration (s): 0.20 | learning rate: 1.027E-04 | global batch size: 256 | lm loss: 2.910099E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.313 | TFLOPs: 8.25 | +31: iteration 19940/ 37905 | consumed samples: 5104640 | consumed tokens: 10454302720 | elapsed time per iteration (s): 0.22 | learning rate: 1.026E-04 | global batch size: 256 | lm loss: 2.973845E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.385 | TFLOPs: 7.47 | +31: iteration 19950/ 37905 | consumed samples: 5107200 | consumed tokens: 10459545600 | elapsed time per iteration (s): 0.24 | learning rate: 1.026E-04 | global batch size: 256 | lm loss: 2.916916E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.014 | TFLOPs: 6.66 | +31: iteration 19960/ 37905 | consumed samples: 5109760 | consumed tokens: 10464788480 | elapsed time per iteration (s): 0.20 | learning rate: 1.025E-04 | global batch size: 256 | lm loss: 2.916345E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.744 | TFLOPs: 8.09 | +31: iteration 19970/ 37905 | consumed samples: 5112320 | consumed tokens: 10470031360 | elapsed time per iteration (s): 0.23 | learning rate: 1.024E-04 | global batch size: 256 | lm loss: 2.960884E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.974 | TFLOPs: 7.06 | +31: iteration 19980/ 37905 | consumed samples: 5114880 | consumed tokens: 10475274240 | elapsed time per iteration (s): 0.21 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 2.960147E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.296 | TFLOPs: 7.94 | +31: iteration 19990/ 37905 | consumed samples: 5117440 | consumed tokens: 10480517120 | elapsed time per iteration (s): 0.26 | learning rate: 1.023E-04 | global batch size: 256 | lm loss: 2.954463E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1002.248 | TFLOPs: 6.38 | + 0: [2022-11-24 15:23:20,852] [INFO] [logging.py:68:log_dist] [Rank 0] step=20000, skipped=0, lr=[0.00010219655616803863, 0.00010219655616803863, 0.00010219655616803863], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 20000/ 37905 | consumed samples: 5120000 | consumed tokens: 10485760000 | elapsed time per iteration (s): 0.23 | learning rate: 1.022E-04 | global batch size: 256 | lm loss: 2.978818E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.601 | TFLOPs: 7.13 | + 0: steps: 20000 loss: 2.9356 iter time (s): 0.229 samples/sec: 1117.105 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 20000 | lm loss value: 2.795371E+00 | lm loss PPL: 1.636871E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 20000 to checkpoints_83m + 0: [2022-11-24 15:23:20,964] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step20000 is begin to save! + 0: [2022-11-24 15:23:20,989] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,077] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,077] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,088] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,122] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,133] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,144] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:23:21,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:23:21,178] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step20000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:23:21,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:23:21,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:23:21,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,254] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:23:21,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:23:21,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-24 15:23:21,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,255] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +10: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,256] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +28: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:23:21,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +31: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,257] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-24 15:23:21,257] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +18: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-24 15:23:21,258] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:23:21,258] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:23:21,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:23:21,259] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:23:21,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:23:21,260] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:23:21,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-24 15:23:21,261] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,261] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:23:21,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:23:21,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:23:21,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:23:21,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:23:21,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-24 15:23:21,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:23:21,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:23:21,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:23:21,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-24 15:23:21,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:23:21,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:23:21,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +10: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:23:21,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-24 15:23:21,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:23:21,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:23:21,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +18: [2022-11-24 15:23:21,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:23:21,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:23:21,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-24 15:23:21,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:23:21,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +11: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +27: [2022-11-24 15:23:21,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:23:21,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:23:21,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: [2022-11-24 15:23:21,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +28: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +31: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +24: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +27: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +13: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +24: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +31: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +11: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:23:21,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +14: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +18: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +14: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +15: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +15: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +18: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +10: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +18: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +29: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +29: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +10: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 2: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +13: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +18: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 3: [2022-11-24 15:23:21,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +20: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +20: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,418] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +25: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +25: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +25: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +30: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +30: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +20: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +26: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +25: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +26: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +12: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 9: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +12: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +21: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +19: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +20: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 7: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +17: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +19: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 5: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +22: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 4: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +23: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +23: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 1: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! +16: [2022-11-24 15:23:21,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,420] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:23:21,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,421] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step20000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 6: [2022-11-24 15:23:21,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step20000 is ready now! + 0: successfully saved checkpoint at iteration 20000 to checkpoints_83m +31: time (ms) | save-checkpoint: 482.51 +31: iteration 20010/ 37905 | consumed samples: 5122560 | consumed tokens: 10491002880 | elapsed time per iteration (s): 0.26 | learning rate: 1.021E-04 | global batch size: 256 | lm loss: 2.947308E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 967.148 | TFLOPs: 6.16 | +31: iteration 20020/ 37905 | consumed samples: 5125120 | consumed tokens: 10496245760 | elapsed time per iteration (s): 0.23 | learning rate: 1.020E-04 | global batch size: 256 | lm loss: 2.918995E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.812 | TFLOPs: 7.07 | +31: iteration 20030/ 37905 | consumed samples: 5127680 | consumed tokens: 10501488640 | elapsed time per iteration (s): 0.21 | learning rate: 1.020E-04 | global batch size: 256 | lm loss: 2.949788E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.940 | TFLOPs: 7.92 | +31: iteration 20040/ 37905 | consumed samples: 5130240 | consumed tokens: 10506731520 | elapsed time per iteration (s): 0.22 | learning rate: 1.019E-04 | global batch size: 256 | lm loss: 2.956384E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.323 | TFLOPs: 7.39 | +31: iteration 20050/ 37905 | consumed samples: 5132800 | consumed tokens: 10511974400 | elapsed time per iteration (s): 0.24 | learning rate: 1.018E-04 | global batch size: 256 | lm loss: 2.929526E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.864 | TFLOPs: 6.82 | +31: iteration 20060/ 37905 | consumed samples: 5135360 | consumed tokens: 10517217280 | elapsed time per iteration (s): 0.23 | learning rate: 1.018E-04 | global batch size: 256 | lm loss: 2.947068E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1136.792 | TFLOPs: 7.24 | +31: iteration 20070/ 37905 | consumed samples: 5137920 | consumed tokens: 10522460160 | elapsed time per iteration (s): 0.20 | learning rate: 1.017E-04 | global batch size: 256 | lm loss: 2.911321E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.123 | TFLOPs: 8.01 | +31: iteration 20080/ 37905 | consumed samples: 5140480 | consumed tokens: 10527703040 | elapsed time per iteration (s): 0.22 | learning rate: 1.016E-04 | global batch size: 256 | lm loss: 2.924607E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.960 | TFLOPs: 7.49 | +31: iteration 20090/ 37905 | consumed samples: 5143040 | consumed tokens: 10532945920 | elapsed time per iteration (s): 0.21 | learning rate: 1.015E-04 | global batch size: 256 | lm loss: 2.893534E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.452 | TFLOPs: 7.83 | +31: iteration 20100/ 37905 | consumed samples: 5145600 | consumed tokens: 10538188800 | elapsed time per iteration (s): 0.21 | learning rate: 1.015E-04 | global batch size: 256 | lm loss: 2.965066E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.513 | TFLOPs: 7.71 | +31: iteration 20110/ 37905 | consumed samples: 5148160 | consumed tokens: 10543431680 | elapsed time per iteration (s): 0.21 | learning rate: 1.014E-04 | global batch size: 256 | lm loss: 2.919791E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.643 | TFLOPs: 7.82 | +31: iteration 20120/ 37905 | consumed samples: 5150720 | consumed tokens: 10548674560 | elapsed time per iteration (s): 0.20 | learning rate: 1.013E-04 | global batch size: 256 | lm loss: 2.928838E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.705 | TFLOPs: 8.32 | +31: iteration 20130/ 37905 | consumed samples: 5153280 | consumed tokens: 10553917440 | elapsed time per iteration (s): 0.21 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 2.942537E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.319 | TFLOPs: 7.69 | +31: iteration 20140/ 37905 | consumed samples: 5155840 | consumed tokens: 10559160320 | elapsed time per iteration (s): 0.22 | learning rate: 1.012E-04 | global batch size: 256 | lm loss: 2.932557E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.185 | TFLOPs: 7.50 | +31: iteration 20150/ 37905 | consumed samples: 5158400 | consumed tokens: 10564403200 | elapsed time per iteration (s): 0.20 | learning rate: 1.011E-04 | global batch size: 256 | lm loss: 2.946223E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.891 | TFLOPs: 7.99 | +31: iteration 20160/ 37905 | consumed samples: 5160960 | consumed tokens: 10569646080 | elapsed time per iteration (s): 0.24 | learning rate: 1.010E-04 | global batch size: 256 | lm loss: 2.985640E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.814 | TFLOPs: 6.90 | +31: iteration 20170/ 37905 | consumed samples: 5163520 | consumed tokens: 10574888960 | elapsed time per iteration (s): 0.25 | learning rate: 1.009E-04 | global batch size: 256 | lm loss: 2.931088E+00 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.923 | TFLOPs: 6.52 | +31: iteration 20180/ 37905 | consumed samples: 5166080 | consumed tokens: 10580131840 | elapsed time per iteration (s): 0.23 | learning rate: 1.009E-04 | global batch size: 256 | lm loss: 2.946414E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.298 | TFLOPs: 7.01 | +31: iteration 20190/ 37905 | consumed samples: 5168640 | consumed tokens: 10585374720 | elapsed time per iteration (s): 0.23 | learning rate: 1.008E-04 | global batch size: 256 | lm loss: 2.937664E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.291 | TFLOPs: 7.13 | +31: iteration 20200/ 37905 | consumed samples: 5171200 | consumed tokens: 10590617600 | elapsed time per iteration (s): 0.21 | learning rate: 1.007E-04 | global batch size: 256 | lm loss: 2.951139E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.831 | TFLOPs: 7.76 | +31: iteration 20210/ 37905 | consumed samples: 5173760 | consumed tokens: 10595860480 | elapsed time per iteration (s): 0.22 | learning rate: 1.006E-04 | global batch size: 256 | lm loss: 2.895815E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.089 | TFLOPs: 7.48 | +31: iteration 20220/ 37905 | consumed samples: 5176320 | consumed tokens: 10601103360 | elapsed time per iteration (s): 0.23 | learning rate: 1.006E-04 | global batch size: 256 | lm loss: 2.914924E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.191 | TFLOPs: 7.19 | +31: iteration 20230/ 37905 | consumed samples: 5178880 | consumed tokens: 10606346240 | elapsed time per iteration (s): 0.20 | learning rate: 1.005E-04 | global batch size: 256 | lm loss: 2.939676E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1262.379 | TFLOPs: 8.04 | +31: iteration 20240/ 37905 | consumed samples: 5181440 | consumed tokens: 10611589120 | elapsed time per iteration (s): 0.23 | learning rate: 1.004E-04 | global batch size: 256 | lm loss: 2.937592E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.034 | TFLOPs: 7.06 | +31: iteration 20250/ 37905 | consumed samples: 5184000 | consumed tokens: 10616832000 | elapsed time per iteration (s): 0.23 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 2.928928E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.174 | TFLOPs: 7.21 | +31: iteration 20260/ 37905 | consumed samples: 5186560 | consumed tokens: 10622074880 | elapsed time per iteration (s): 0.22 | learning rate: 1.003E-04 | global batch size: 256 | lm loss: 2.926482E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1180.475 | TFLOPs: 7.52 | +31: iteration 20270/ 37905 | consumed samples: 5189120 | consumed tokens: 10627317760 | elapsed time per iteration (s): 0.23 | learning rate: 1.002E-04 | global batch size: 256 | lm loss: 2.936056E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.868 | TFLOPs: 7.18 | +31: iteration 20280/ 37905 | consumed samples: 5191680 | consumed tokens: 10632560640 | elapsed time per iteration (s): 0.23 | learning rate: 1.001E-04 | global batch size: 256 | lm loss: 2.944207E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.143 | TFLOPs: 7.23 | +31: iteration 20290/ 37905 | consumed samples: 5194240 | consumed tokens: 10637803520 | elapsed time per iteration (s): 0.22 | learning rate: 1.000E-04 | global batch size: 256 | lm loss: 2.980172E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.479 | TFLOPs: 7.38 | +31: iteration 20300/ 37905 | consumed samples: 5196800 | consumed tokens: 10643046400 | elapsed time per iteration (s): 0.20 | learning rate: 9.997E-05 | global batch size: 256 | lm loss: 2.919207E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.009 | TFLOPs: 8.36 | +31: iteration 20310/ 37905 | consumed samples: 5199360 | consumed tokens: 10648289280 | elapsed time per iteration (s): 0.27 | learning rate: 9.990E-05 | global batch size: 256 | lm loss: 2.927951E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 943.259 | TFLOPs: 6.01 | +31: iteration 20320/ 37905 | consumed samples: 5201920 | consumed tokens: 10653532160 | elapsed time per iteration (s): 0.26 | learning rate: 9.982E-05 | global batch size: 256 | lm loss: 2.944143E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 966.259 | TFLOPs: 6.15 | +31: iteration 20330/ 37905 | consumed samples: 5204480 | consumed tokens: 10658775040 | elapsed time per iteration (s): 0.24 | learning rate: 9.975E-05 | global batch size: 256 | lm loss: 2.963162E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.466 | TFLOPs: 6.66 | +31: iteration 20340/ 37905 | consumed samples: 5207040 | consumed tokens: 10664017920 | elapsed time per iteration (s): 0.30 | learning rate: 9.967E-05 | global batch size: 256 | lm loss: 2.929156E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 848.404 | TFLOPs: 5.40 | +31: iteration 20350/ 37905 | consumed samples: 5209600 | consumed tokens: 10669260800 | elapsed time per iteration (s): 0.22 | learning rate: 9.960E-05 | global batch size: 256 | lm loss: 2.884830E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.432 | TFLOPs: 7.30 | +31: iteration 20360/ 37905 | consumed samples: 5212160 | consumed tokens: 10674503680 | elapsed time per iteration (s): 0.23 | learning rate: 9.953E-05 | global batch size: 256 | lm loss: 2.945134E+00 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.163 | TFLOPs: 6.98 | +31: iteration 20370/ 37905 | consumed samples: 5214720 | consumed tokens: 10679746560 | elapsed time per iteration (s): 0.20 | learning rate: 9.945E-05 | global batch size: 256 | lm loss: 2.917072E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.267 | TFLOPs: 8.11 | +31: iteration 20380/ 37905 | consumed samples: 5217280 | consumed tokens: 10684989440 | elapsed time per iteration (s): 0.20 | learning rate: 9.938E-05 | global batch size: 256 | lm loss: 2.947463E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.408 | TFLOPs: 8.14 | +31: iteration 20390/ 37905 | consumed samples: 5219840 | consumed tokens: 10690232320 | elapsed time per iteration (s): 0.21 | learning rate: 9.930E-05 | global batch size: 256 | lm loss: 2.915978E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.753 | TFLOPs: 7.65 | +31: iteration 20400/ 37905 | consumed samples: 5222400 | consumed tokens: 10695475200 | elapsed time per iteration (s): 0.23 | learning rate: 9.923E-05 | global batch size: 256 | lm loss: 2.965445E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.298 | TFLOPs: 7.12 | +31: iteration 20410/ 37905 | consumed samples: 5224960 | consumed tokens: 10700718080 | elapsed time per iteration (s): 0.18 | learning rate: 9.915E-05 | global batch size: 256 | lm loss: 2.922203E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1384.279 | TFLOPs: 8.82 | +31: iteration 20420/ 37905 | consumed samples: 5227520 | consumed tokens: 10705960960 | elapsed time per iteration (s): 0.22 | learning rate: 9.908E-05 | global batch size: 256 | lm loss: 2.955954E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.919 | TFLOPs: 7.38 | +31: iteration 20430/ 37905 | consumed samples: 5230080 | consumed tokens: 10711203840 | elapsed time per iteration (s): 0.25 | learning rate: 9.901E-05 | global batch size: 256 | lm loss: 2.944981E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.158 | TFLOPs: 6.57 | +31: iteration 20440/ 37905 | consumed samples: 5232640 | consumed tokens: 10716446720 | elapsed time per iteration (s): 0.21 | learning rate: 9.893E-05 | global batch size: 256 | lm loss: 2.940641E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.061 | TFLOPs: 7.78 | +31: iteration 20450/ 37905 | consumed samples: 5235200 | consumed tokens: 10721689600 | elapsed time per iteration (s): 0.21 | learning rate: 9.886E-05 | global batch size: 256 | lm loss: 2.934356E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.334 | TFLOPs: 7.63 | +31: iteration 20460/ 37905 | consumed samples: 5237760 | consumed tokens: 10726932480 | elapsed time per iteration (s): 0.25 | learning rate: 9.878E-05 | global batch size: 256 | lm loss: 2.931422E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.379 | TFLOPs: 6.44 | +31: iteration 20470/ 37905 | consumed samples: 5240320 | consumed tokens: 10732175360 | elapsed time per iteration (s): 0.23 | learning rate: 9.871E-05 | global batch size: 256 | lm loss: 2.936460E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.793 | TFLOPs: 6.96 | +31: iteration 20480/ 37905 | consumed samples: 5242880 | consumed tokens: 10737418240 | elapsed time per iteration (s): 0.21 | learning rate: 9.864E-05 | global batch size: 256 | lm loss: 2.944641E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.311 | TFLOPs: 7.80 | +31: iteration 20490/ 37905 | consumed samples: 5245440 | consumed tokens: 10742661120 | elapsed time per iteration (s): 0.24 | learning rate: 9.856E-05 | global batch size: 256 | lm loss: 2.944136E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.749 | TFLOPs: 6.68 | +31: iteration 20500/ 37905 | consumed samples: 5248000 | consumed tokens: 10747904000 | elapsed time per iteration (s): 0.25 | learning rate: 9.849E-05 | global batch size: 256 | lm loss: 2.948798E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.193 | TFLOPs: 6.63 | +31: iteration 20510/ 37905 | consumed samples: 5250560 | consumed tokens: 10753146880 | elapsed time per iteration (s): 0.22 | learning rate: 9.841E-05 | global batch size: 256 | lm loss: 2.934691E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.476 | TFLOPs: 7.51 | +31: iteration 20520/ 37905 | consumed samples: 5253120 | consumed tokens: 10758389760 | elapsed time per iteration (s): 0.26 | learning rate: 9.834E-05 | global batch size: 256 | lm loss: 2.991611E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.477 | TFLOPs: 6.28 | +31: iteration 20530/ 37905 | consumed samples: 5255680 | consumed tokens: 10763632640 | elapsed time per iteration (s): 0.20 | learning rate: 9.827E-05 | global batch size: 256 | lm loss: 2.951952E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.386 | TFLOPs: 8.07 | +31: iteration 20540/ 37905 | consumed samples: 5258240 | consumed tokens: 10768875520 | elapsed time per iteration (s): 0.21 | learning rate: 9.819E-05 | global batch size: 256 | lm loss: 2.923780E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.594 | TFLOPs: 7.85 | +31: iteration 20550/ 37905 | consumed samples: 5260800 | consumed tokens: 10774118400 | elapsed time per iteration (s): 0.22 | learning rate: 9.812E-05 | global batch size: 256 | lm loss: 2.952254E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.514 | TFLOPs: 7.35 | +31: iteration 20560/ 37905 | consumed samples: 5263360 | consumed tokens: 10779361280 | elapsed time per iteration (s): 0.19 | learning rate: 9.805E-05 | global batch size: 256 | lm loss: 2.938883E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.005 | TFLOPs: 8.43 | +31: iteration 20570/ 37905 | consumed samples: 5265920 | consumed tokens: 10784604160 | elapsed time per iteration (s): 0.22 | learning rate: 9.797E-05 | global batch size: 256 | lm loss: 2.927083E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.305 | TFLOPs: 7.56 | +31: iteration 20580/ 37905 | consumed samples: 5268480 | consumed tokens: 10789847040 | elapsed time per iteration (s): 0.21 | learning rate: 9.790E-05 | global batch size: 256 | lm loss: 2.903091E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.629 | TFLOPs: 7.68 | +31: iteration 20590/ 37905 | consumed samples: 5271040 | consumed tokens: 10795089920 | elapsed time per iteration (s): 0.21 | learning rate: 9.782E-05 | global batch size: 256 | lm loss: 2.945054E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.821 | TFLOPs: 7.76 | +31: iteration 20600/ 37905 | consumed samples: 5273600 | consumed tokens: 10800332800 | elapsed time per iteration (s): 0.22 | learning rate: 9.775E-05 | global batch size: 256 | lm loss: 2.911054E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.234 | TFLOPs: 7.26 | +31: iteration 20610/ 37905 | consumed samples: 5276160 | consumed tokens: 10805575680 | elapsed time per iteration (s): 0.24 | learning rate: 9.768E-05 | global batch size: 256 | lm loss: 2.922468E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.405 | TFLOPs: 6.79 | +31: iteration 20620/ 37905 | consumed samples: 5278720 | consumed tokens: 10810818560 | elapsed time per iteration (s): 0.23 | learning rate: 9.760E-05 | global batch size: 256 | lm loss: 2.912827E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.017 | TFLOPs: 6.94 | +31: iteration 20630/ 37905 | consumed samples: 5281280 | consumed tokens: 10816061440 | elapsed time per iteration (s): 0.21 | learning rate: 9.753E-05 | global batch size: 256 | lm loss: 2.965575E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.084 | TFLOPs: 7.75 | +31: iteration 20640/ 37905 | consumed samples: 5283840 | consumed tokens: 10821304320 | elapsed time per iteration (s): 0.23 | learning rate: 9.745E-05 | global batch size: 256 | lm loss: 2.947793E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.776 | TFLOPs: 7.04 | +31: iteration 20650/ 37905 | consumed samples: 5286400 | consumed tokens: 10826547200 | elapsed time per iteration (s): 0.21 | learning rate: 9.738E-05 | global batch size: 256 | lm loss: 2.936910E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.292 | TFLOPs: 7.88 | +31: iteration 20660/ 37905 | consumed samples: 5288960 | consumed tokens: 10831790080 | elapsed time per iteration (s): 0.25 | learning rate: 9.731E-05 | global batch size: 256 | lm loss: 2.968675E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.270 | TFLOPs: 6.64 | +31: iteration 20670/ 37905 | consumed samples: 5291520 | consumed tokens: 10837032960 | elapsed time per iteration (s): 0.21 | learning rate: 9.723E-05 | global batch size: 256 | lm loss: 2.942426E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.439 | TFLOPs: 7.86 | +31: iteration 20680/ 37905 | consumed samples: 5294080 | consumed tokens: 10842275840 | elapsed time per iteration (s): 0.25 | learning rate: 9.716E-05 | global batch size: 256 | lm loss: 2.917080E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.451 | TFLOPs: 6.51 | +31: iteration 20690/ 37905 | consumed samples: 5296640 | consumed tokens: 10847518720 | elapsed time per iteration (s): 0.22 | learning rate: 9.708E-05 | global batch size: 256 | lm loss: 2.935860E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.196 | TFLOPs: 7.56 | +31: iteration 20700/ 37905 | consumed samples: 5299200 | consumed tokens: 10852761600 | elapsed time per iteration (s): 0.20 | learning rate: 9.701E-05 | global batch size: 256 | lm loss: 2.943768E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.096 | TFLOPs: 8.15 | +31: iteration 20710/ 37905 | consumed samples: 5301760 | consumed tokens: 10858004480 | elapsed time per iteration (s): 0.24 | learning rate: 9.694E-05 | global batch size: 256 | lm loss: 2.910514E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.565 | TFLOPs: 6.78 | +31: iteration 20720/ 37905 | consumed samples: 5304320 | consumed tokens: 10863247360 | elapsed time per iteration (s): 0.25 | learning rate: 9.686E-05 | global batch size: 256 | lm loss: 2.922054E+00 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.953 | TFLOPs: 6.57 | +31: iteration 20730/ 37905 | consumed samples: 5306880 | consumed tokens: 10868490240 | elapsed time per iteration (s): 0.21 | learning rate: 9.679E-05 | global batch size: 256 | lm loss: 2.940123E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.954 | TFLOPs: 7.62 | +31: iteration 20740/ 37905 | consumed samples: 5309440 | consumed tokens: 10873733120 | elapsed time per iteration (s): 0.20 | learning rate: 9.672E-05 | global batch size: 256 | lm loss: 2.925920E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1259.399 | TFLOPs: 8.02 | +31: iteration 20750/ 37905 | consumed samples: 5312000 | consumed tokens: 10878976000 | elapsed time per iteration (s): 0.21 | learning rate: 9.664E-05 | global batch size: 256 | lm loss: 2.945917E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.395 | TFLOPs: 7.61 | +31: iteration 20760/ 37905 | consumed samples: 5314560 | consumed tokens: 10884218880 | elapsed time per iteration (s): 0.20 | learning rate: 9.657E-05 | global batch size: 256 | lm loss: 2.947877E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.208 | TFLOPs: 7.99 | +31: iteration 20770/ 37905 | consumed samples: 5317120 | consumed tokens: 10889461760 | elapsed time per iteration (s): 0.25 | learning rate: 9.649E-05 | global batch size: 256 | lm loss: 2.940728E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.015 | TFLOPs: 6.57 | +31: iteration 20780/ 37905 | consumed samples: 5319680 | consumed tokens: 10894704640 | elapsed time per iteration (s): 0.25 | learning rate: 9.642E-05 | global batch size: 256 | lm loss: 2.937265E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.941 | TFLOPs: 6.64 | +31: iteration 20790/ 37905 | consumed samples: 5322240 | consumed tokens: 10899947520 | elapsed time per iteration (s): 0.20 | learning rate: 9.635E-05 | global batch size: 256 | lm loss: 2.948002E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.846 | TFLOPs: 8.04 | +31: iteration 20800/ 37905 | consumed samples: 5324800 | consumed tokens: 10905190400 | elapsed time per iteration (s): 0.23 | learning rate: 9.627E-05 | global batch size: 256 | lm loss: 2.967317E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.415 | TFLOPs: 7.06 | +31: iteration 20810/ 37905 | consumed samples: 5327360 | consumed tokens: 10910433280 | elapsed time per iteration (s): 0.19 | learning rate: 9.620E-05 | global batch size: 256 | lm loss: 2.935783E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.263 | TFLOPs: 8.38 | +31: iteration 20820/ 37905 | consumed samples: 5329920 | consumed tokens: 10915676160 | elapsed time per iteration (s): 0.20 | learning rate: 9.613E-05 | global batch size: 256 | lm loss: 2.938175E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.468 | TFLOPs: 8.19 | +31: iteration 20830/ 37905 | consumed samples: 5332480 | consumed tokens: 10920919040 | elapsed time per iteration (s): 0.22 | learning rate: 9.605E-05 | global batch size: 256 | lm loss: 2.894921E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.101 | TFLOPs: 7.53 | +31: iteration 20840/ 37905 | consumed samples: 5335040 | consumed tokens: 10926161920 | elapsed time per iteration (s): 0.22 | learning rate: 9.598E-05 | global batch size: 256 | lm loss: 2.933356E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.133 | TFLOPs: 7.52 | +31: iteration 20850/ 37905 | consumed samples: 5337600 | consumed tokens: 10931404800 | elapsed time per iteration (s): 0.21 | learning rate: 9.590E-05 | global batch size: 256 | lm loss: 2.942718E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.080 | TFLOPs: 7.68 | +31: iteration 20860/ 37905 | consumed samples: 5340160 | consumed tokens: 10936647680 | elapsed time per iteration (s): 0.24 | learning rate: 9.583E-05 | global batch size: 256 | lm loss: 2.946697E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.875 | TFLOPs: 6.75 | +31: iteration 20870/ 37905 | consumed samples: 5342720 | consumed tokens: 10941890560 | elapsed time per iteration (s): 0.20 | learning rate: 9.576E-05 | global batch size: 256 | lm loss: 2.953062E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.734 | TFLOPs: 8.05 | +31: iteration 20880/ 37905 | consumed samples: 5345280 | consumed tokens: 10947133440 | elapsed time per iteration (s): 0.22 | learning rate: 9.568E-05 | global batch size: 256 | lm loss: 2.949516E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.099 | TFLOPs: 7.32 | +31: iteration 20890/ 37905 | consumed samples: 5347840 | consumed tokens: 10952376320 | elapsed time per iteration (s): 0.20 | learning rate: 9.561E-05 | global batch size: 256 | lm loss: 2.922728E+00 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.139 | TFLOPs: 7.96 | +31: iteration 20900/ 37905 | consumed samples: 5350400 | consumed tokens: 10957619200 | elapsed time per iteration (s): 0.25 | learning rate: 9.554E-05 | global batch size: 256 | lm loss: 2.924737E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1023.014 | TFLOPs: 6.52 | +31: iteration 20910/ 37905 | consumed samples: 5352960 | consumed tokens: 10962862080 | elapsed time per iteration (s): 0.22 | learning rate: 9.546E-05 | global batch size: 256 | lm loss: 2.920280E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.294 | TFLOPs: 7.47 | +31: iteration 20920/ 37905 | consumed samples: 5355520 | consumed tokens: 10968104960 | elapsed time per iteration (s): 0.23 | learning rate: 9.539E-05 | global batch size: 256 | lm loss: 2.932635E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.686 | TFLOPs: 7.00 | +31: iteration 20930/ 37905 | consumed samples: 5358080 | consumed tokens: 10973347840 | elapsed time per iteration (s): 0.23 | learning rate: 9.532E-05 | global batch size: 256 | lm loss: 2.935176E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.947 | TFLOPs: 6.98 | +31: iteration 20940/ 37905 | consumed samples: 5360640 | consumed tokens: 10978590720 | elapsed time per iteration (s): 0.19 | learning rate: 9.524E-05 | global batch size: 256 | lm loss: 2.900990E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.709 | TFLOPs: 8.39 | +31: iteration 20950/ 37905 | consumed samples: 5363200 | consumed tokens: 10983833600 | elapsed time per iteration (s): 0.23 | learning rate: 9.517E-05 | global batch size: 256 | lm loss: 2.927306E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.792 | TFLOPs: 7.00 | +31: iteration 20960/ 37905 | consumed samples: 5365760 | consumed tokens: 10989076480 | elapsed time per iteration (s): 0.23 | learning rate: 9.509E-05 | global batch size: 256 | lm loss: 2.929171E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.778 | TFLOPs: 7.10 | +31: iteration 20970/ 37905 | consumed samples: 5368320 | consumed tokens: 10994319360 | elapsed time per iteration (s): 0.22 | learning rate: 9.502E-05 | global batch size: 256 | lm loss: 2.919636E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.871 | TFLOPs: 7.43 | +31: iteration 20980/ 37905 | consumed samples: 5370880 | consumed tokens: 10999562240 | elapsed time per iteration (s): 0.24 | learning rate: 9.495E-05 | global batch size: 256 | lm loss: 2.906651E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.668 | TFLOPs: 6.80 | +31: iteration 20990/ 37905 | consumed samples: 5373440 | consumed tokens: 11004805120 | elapsed time per iteration (s): 0.20 | learning rate: 9.487E-05 | global batch size: 256 | lm loss: 2.939401E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.254 | TFLOPs: 8.05 | +31: iteration 21000/ 37905 | consumed samples: 5376000 | consumed tokens: 11010048000 | elapsed time per iteration (s): 0.24 | learning rate: 9.480E-05 | global batch size: 256 | lm loss: 2.945018E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.192 | TFLOPs: 6.77 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 21000 | lm loss value: 2.855085E+00 | lm loss PPL: 1.737592E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 21000 to checkpoints_83m + 0: [2022-11-24 15:27:04,173] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step21000 is begin to save! + 0: [2022-11-24 15:27:04,181] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,266] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,277] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,288] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,299] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,310] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,321] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,332] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,343] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,354] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,365] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:27:04,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:27:04,367] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step21000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:27:04,367] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:27:04,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:27:04,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,442] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:27:04,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +31: [2022-11-24 15:27:04,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +17: [2022-11-24 15:27:04,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,443] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 9: [2022-11-24 15:27:04,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +13: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,444] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +13: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +28: [2022-11-24 15:27:04,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:27:04,445] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:27:04,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:27:04,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 4: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +30: [2022-11-24 15:27:04,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +22: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +30: [2022-11-24 15:27:04,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +22: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +30: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +15: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:27:04,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +17: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:27:04,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +19: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +13: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:27:04,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 9: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 9: [2022-11-24 15:27:04,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +27: [2022-11-24 15:27:04,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +25: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:27:04,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:27:04,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:27:04,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:27:04,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +14: [2022-11-24 15:27:04,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +14: [2022-11-24 15:27:04,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:27:04,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:27:04,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 4: [2022-11-24 15:27:04,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +30: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +15: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:27:04,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:27:04,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:27:04,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +17: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +31: [2022-11-24 15:27:04,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:27:04,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:27:04,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +24: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +19: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +24: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +27: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +28: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 9: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +25: [2022-11-24 15:27:04,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:27:04,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:27:04,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:27:04,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:27:04,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:27:04,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:27:04,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 4: [2022-11-24 15:27:04,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +30: [2022-11-24 15:27:04,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +15: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +17: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:27:04,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +19: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:27:04,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:27:04,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:27:04,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +28: [2022-11-24 15:27:04,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +28: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +13: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 9: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +25: [2022-11-24 15:27:04,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +14: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:27:04,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:27:04,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 4: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +30: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:27:04,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +15: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +17: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:27:04,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:27:04,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +31: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:27:04,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +22: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +19: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:27:04,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 15:27:04,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +13: [2022-11-24 15:27:04,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 15:27:04,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +28: [2022-11-24 15:27:04,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +28: [2022-11-24 15:27:04,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:27:04,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 9: [2022-11-24 15:27:04,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +25: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:27:04,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:27:04,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:27:04,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 4: [2022-11-24 15:27:04,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +30: [2022-11-24 15:27:04,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:27:04,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:27:04,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:27:04,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +16: [2022-11-24 15:27:04,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +15: [2022-11-24 15:27:04,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +17: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:27:04,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:27:04,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:27:04,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:27:04,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:27:04,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:27:04,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +19: [2022-11-24 15:27:04,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:27:04,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +23: [2022-11-24 15:27:04,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +27: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +13: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:27:04,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 9: [2022-11-24 15:27:04,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +25: [2022-11-24 15:27:04,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +14: [2022-11-24 15:27:04,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:27:04,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:27:04,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +11: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:27:04,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:27:04,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +30: [2022-11-24 15:27:04,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:27:04,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:27:04,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:27:04,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 4: [2022-11-24 15:27:04,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +15: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:27:04,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +29: [2022-11-24 15:27:04,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +17: [2022-11-24 15:27:04,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:27:04,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:27:04,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:27:04,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:27:04,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +24: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +19: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:27:04,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +23: [2022-11-24 15:27:04,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +31: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +13: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 15:27:04,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +27: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +25: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:27:04,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +14: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +11: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +13: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +15: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 2: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +29: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +15: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 7: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +30: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 6: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +17: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +30: [2022-11-24 15:27:04,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +16: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 4: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +23: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 5: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +25: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +30: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +19: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +22: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +14: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +26: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +18: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +16: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +19: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +14: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +20: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +21: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +23: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +11: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +16: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 1: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +18: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +12: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +28: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +27: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +24: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +21: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +11: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +12: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +28: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +27: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +27: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +24: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +22: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 3: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 8: [2022-11-24 15:27:04,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +10: [2022-11-24 15:27:04,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:27:04,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:27:04,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! +31: [2022-11-24 15:27:04,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:27:04,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step21000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:27:04,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step21000 is ready now! + 0: successfully saved checkpoint at iteration 21000 to checkpoints_83m +31: time (ms) | save-checkpoint: 323.91 +31: iteration 21010/ 37905 | consumed samples: 5378560 | consumed tokens: 11015290880 | elapsed time per iteration (s): 0.26 | learning rate: 9.473E-05 | global batch size: 256 | lm loss: 2.964096E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 994.711 | TFLOPs: 6.34 | +31: iteration 21020/ 37905 | consumed samples: 5381120 | consumed tokens: 11020533760 | elapsed time per iteration (s): 0.22 | learning rate: 9.465E-05 | global batch size: 256 | lm loss: 2.953530E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.140 | TFLOPs: 7.38 | +31: iteration 21030/ 37905 | consumed samples: 5383680 | consumed tokens: 11025776640 | elapsed time per iteration (s): 0.21 | learning rate: 9.458E-05 | global batch size: 256 | lm loss: 2.969489E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.172 | TFLOPs: 7.59 | +31: iteration 21040/ 37905 | consumed samples: 5386240 | consumed tokens: 11031019520 | elapsed time per iteration (s): 0.21 | learning rate: 9.451E-05 | global batch size: 256 | lm loss: 2.920052E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.767 | TFLOPs: 7.91 | +31: iteration 21050/ 37905 | consumed samples: 5388800 | consumed tokens: 11036262400 | elapsed time per iteration (s): 0.22 | learning rate: 9.443E-05 | global batch size: 256 | lm loss: 2.940079E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.090 | TFLOPs: 7.55 | +31: iteration 21060/ 37905 | consumed samples: 5391360 | consumed tokens: 11041505280 | elapsed time per iteration (s): 0.22 | learning rate: 9.436E-05 | global batch size: 256 | lm loss: 2.967698E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.600 | TFLOPs: 7.33 | +31: iteration 21070/ 37905 | consumed samples: 5393920 | consumed tokens: 11046748160 | elapsed time per iteration (s): 0.19 | learning rate: 9.429E-05 | global batch size: 256 | lm loss: 2.918128E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.746 | TFLOPs: 8.44 | +31: iteration 21080/ 37905 | consumed samples: 5396480 | consumed tokens: 11051991040 | elapsed time per iteration (s): 0.23 | learning rate: 9.421E-05 | global batch size: 256 | lm loss: 2.911443E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.782 | TFLOPs: 7.14 | +31: iteration 21090/ 37905 | consumed samples: 5399040 | consumed tokens: 11057233920 | elapsed time per iteration (s): 0.21 | learning rate: 9.414E-05 | global batch size: 256 | lm loss: 2.915856E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.495 | TFLOPs: 7.91 | +31: iteration 21100/ 37905 | consumed samples: 5401600 | consumed tokens: 11062476800 | elapsed time per iteration (s): 0.23 | learning rate: 9.407E-05 | global batch size: 256 | lm loss: 2.923183E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.857 | TFLOPs: 7.01 | +31: iteration 21110/ 37905 | consumed samples: 5404160 | consumed tokens: 11067719680 | elapsed time per iteration (s): 0.21 | learning rate: 9.399E-05 | global batch size: 256 | lm loss: 2.959537E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.948 | TFLOPs: 7.58 | +31: iteration 21120/ 37905 | consumed samples: 5406720 | consumed tokens: 11072962560 | elapsed time per iteration (s): 0.20 | learning rate: 9.392E-05 | global batch size: 256 | lm loss: 2.957914E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.669 | TFLOPs: 8.14 | +31: iteration 21130/ 37905 | consumed samples: 5409280 | consumed tokens: 11078205440 | elapsed time per iteration (s): 0.23 | learning rate: 9.385E-05 | global batch size: 256 | lm loss: 2.917643E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.396 | TFLOPs: 7.21 | +31: iteration 21140/ 37905 | consumed samples: 5411840 | consumed tokens: 11083448320 | elapsed time per iteration (s): 0.24 | learning rate: 9.377E-05 | global batch size: 256 | lm loss: 2.933806E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.584 | TFLOPs: 6.80 | +31: iteration 21150/ 37905 | consumed samples: 5414400 | consumed tokens: 11088691200 | elapsed time per iteration (s): 0.25 | learning rate: 9.370E-05 | global batch size: 256 | lm loss: 2.955635E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.066 | TFLOPs: 6.48 | +31: iteration 21160/ 37905 | consumed samples: 5416960 | consumed tokens: 11093934080 | elapsed time per iteration (s): 0.24 | learning rate: 9.363E-05 | global batch size: 256 | lm loss: 2.939275E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.471 | TFLOPs: 6.86 | +31: iteration 21170/ 37905 | consumed samples: 5419520 | consumed tokens: 11099176960 | elapsed time per iteration (s): 0.21 | learning rate: 9.355E-05 | global batch size: 256 | lm loss: 2.918160E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.136 | TFLOPs: 7.59 | +31: iteration 21180/ 37905 | consumed samples: 5422080 | consumed tokens: 11104419840 | elapsed time per iteration (s): 0.21 | learning rate: 9.348E-05 | global batch size: 256 | lm loss: 2.915915E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.788 | TFLOPs: 7.65 | +31: iteration 21190/ 37905 | consumed samples: 5424640 | consumed tokens: 11109662720 | elapsed time per iteration (s): 0.20 | learning rate: 9.341E-05 | global batch size: 256 | lm loss: 2.936824E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.620 | TFLOPs: 8.25 | +31: iteration 21200/ 37905 | consumed samples: 5427200 | consumed tokens: 11114905600 | elapsed time per iteration (s): 0.20 | learning rate: 9.333E-05 | global batch size: 256 | lm loss: 2.923589E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.752 | TFLOPs: 8.12 | +31: iteration 21210/ 37905 | consumed samples: 5429760 | consumed tokens: 11120148480 | elapsed time per iteration (s): 0.21 | learning rate: 9.326E-05 | global batch size: 256 | lm loss: 2.906339E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1208.248 | TFLOPs: 7.70 | +31: iteration 21220/ 37905 | consumed samples: 5432320 | consumed tokens: 11125391360 | elapsed time per iteration (s): 0.22 | learning rate: 9.319E-05 | global batch size: 256 | lm loss: 2.930620E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.564 | TFLOPs: 7.40 | +31: iteration 21230/ 37905 | consumed samples: 5434880 | consumed tokens: 11130634240 | elapsed time per iteration (s): 0.20 | learning rate: 9.311E-05 | global batch size: 256 | lm loss: 2.914762E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.977 | TFLOPs: 8.22 | +31: iteration 21240/ 37905 | consumed samples: 5437440 | consumed tokens: 11135877120 | elapsed time per iteration (s): 0.21 | learning rate: 9.304E-05 | global batch size: 256 | lm loss: 2.892999E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.845 | TFLOPs: 7.71 | +31: iteration 21250/ 37905 | consumed samples: 5440000 | consumed tokens: 11141120000 | elapsed time per iteration (s): 0.19 | learning rate: 9.297E-05 | global batch size: 256 | lm loss: 2.975960E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.336 | TFLOPs: 8.40 | +31: iteration 21260/ 37905 | consumed samples: 5442560 | consumed tokens: 11146362880 | elapsed time per iteration (s): 0.20 | learning rate: 9.289E-05 | global batch size: 256 | lm loss: 2.942851E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.616 | TFLOPs: 8.12 | +31: iteration 21270/ 37905 | consumed samples: 5445120 | consumed tokens: 11151605760 | elapsed time per iteration (s): 0.22 | learning rate: 9.282E-05 | global batch size: 256 | lm loss: 2.909461E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.145 | TFLOPs: 7.45 | +31: iteration 21280/ 37905 | consumed samples: 5447680 | consumed tokens: 11156848640 | elapsed time per iteration (s): 0.20 | learning rate: 9.275E-05 | global batch size: 256 | lm loss: 2.931359E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.997 | TFLOPs: 8.33 | +31: iteration 21290/ 37905 | consumed samples: 5450240 | consumed tokens: 11162091520 | elapsed time per iteration (s): 0.22 | learning rate: 9.267E-05 | global batch size: 256 | lm loss: 2.985618E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.888 | TFLOPs: 7.41 | +31: iteration 21300/ 37905 | consumed samples: 5452800 | consumed tokens: 11167334400 | elapsed time per iteration (s): 0.22 | learning rate: 9.260E-05 | global batch size: 256 | lm loss: 2.930545E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.947 | TFLOPs: 7.30 | +31: iteration 21310/ 37905 | consumed samples: 5455360 | consumed tokens: 11172577280 | elapsed time per iteration (s): 0.22 | learning rate: 9.253E-05 | global batch size: 256 | lm loss: 2.916171E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.477 | TFLOPs: 7.54 | +31: iteration 21320/ 37905 | consumed samples: 5457920 | consumed tokens: 11177820160 | elapsed time per iteration (s): 0.21 | learning rate: 9.245E-05 | global batch size: 256 | lm loss: 2.945505E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.297 | TFLOPs: 7.66 | +31: iteration 21330/ 37905 | consumed samples: 5460480 | consumed tokens: 11183063040 | elapsed time per iteration (s): 0.22 | learning rate: 9.238E-05 | global batch size: 256 | lm loss: 2.913730E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.782 | TFLOPs: 7.51 | +31: iteration 21340/ 37905 | consumed samples: 5463040 | consumed tokens: 11188305920 | elapsed time per iteration (s): 0.21 | learning rate: 9.231E-05 | global batch size: 256 | lm loss: 2.928797E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1230.160 | TFLOPs: 7.83 | +31: iteration 21350/ 37905 | consumed samples: 5465600 | consumed tokens: 11193548800 | elapsed time per iteration (s): 0.21 | learning rate: 9.223E-05 | global batch size: 256 | lm loss: 2.954771E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.989 | TFLOPs: 7.66 | +31: iteration 21360/ 37905 | consumed samples: 5468160 | consumed tokens: 11198791680 | elapsed time per iteration (s): 0.21 | learning rate: 9.216E-05 | global batch size: 256 | lm loss: 2.958621E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.765 | TFLOPs: 7.82 | +31: iteration 21370/ 37905 | consumed samples: 5470720 | consumed tokens: 11204034560 | elapsed time per iteration (s): 0.23 | learning rate: 9.209E-05 | global batch size: 256 | lm loss: 2.960008E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.816 | TFLOPs: 7.04 | +31: iteration 21380/ 37905 | consumed samples: 5473280 | consumed tokens: 11209277440 | elapsed time per iteration (s): 0.21 | learning rate: 9.201E-05 | global batch size: 256 | lm loss: 2.895293E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1198.345 | TFLOPs: 7.63 | +31: iteration 21390/ 37905 | consumed samples: 5475840 | consumed tokens: 11214520320 | elapsed time per iteration (s): 0.23 | learning rate: 9.194E-05 | global batch size: 256 | lm loss: 2.939093E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.443 | TFLOPs: 7.17 | +31: iteration 21400/ 37905 | consumed samples: 5478400 | consumed tokens: 11219763200 | elapsed time per iteration (s): 0.21 | learning rate: 9.187E-05 | global batch size: 256 | lm loss: 2.932639E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.596 | TFLOPs: 7.77 | +31: iteration 21410/ 37905 | consumed samples: 5480960 | consumed tokens: 11225006080 | elapsed time per iteration (s): 0.24 | learning rate: 9.180E-05 | global batch size: 256 | lm loss: 2.959153E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.741 | TFLOPs: 6.80 | +31: iteration 21420/ 37905 | consumed samples: 5483520 | consumed tokens: 11230248960 | elapsed time per iteration (s): 0.20 | learning rate: 9.172E-05 | global batch size: 256 | lm loss: 2.941485E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.037 | TFLOPs: 7.97 | +31: iteration 21430/ 37905 | consumed samples: 5486080 | consumed tokens: 11235491840 | elapsed time per iteration (s): 0.20 | learning rate: 9.165E-05 | global batch size: 256 | lm loss: 2.967908E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.884 | TFLOPs: 8.07 | +31: iteration 21440/ 37905 | consumed samples: 5488640 | consumed tokens: 11240734720 | elapsed time per iteration (s): 0.22 | learning rate: 9.158E-05 | global batch size: 256 | lm loss: 2.952007E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.261 | TFLOPs: 7.29 | +31: iteration 21450/ 37905 | consumed samples: 5491200 | consumed tokens: 11245977600 | elapsed time per iteration (s): 0.23 | learning rate: 9.150E-05 | global batch size: 256 | lm loss: 2.943861E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.824 | TFLOPs: 7.06 | +31: iteration 21460/ 37905 | consumed samples: 5493760 | consumed tokens: 11251220480 | elapsed time per iteration (s): 0.21 | learning rate: 9.143E-05 | global batch size: 256 | lm loss: 2.917206E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.878 | TFLOPs: 7.68 | +31: iteration 21470/ 37905 | consumed samples: 5496320 | consumed tokens: 11256463360 | elapsed time per iteration (s): 0.20 | learning rate: 9.136E-05 | global batch size: 256 | lm loss: 2.919561E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1298.726 | TFLOPs: 8.27 | +31: iteration 21480/ 37905 | consumed samples: 5498880 | consumed tokens: 11261706240 | elapsed time per iteration (s): 0.23 | learning rate: 9.128E-05 | global batch size: 256 | lm loss: 2.926173E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.832 | TFLOPs: 7.17 | +31: iteration 21490/ 37905 | consumed samples: 5501440 | consumed tokens: 11266949120 | elapsed time per iteration (s): 0.25 | learning rate: 9.121E-05 | global batch size: 256 | lm loss: 2.966291E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1013.888 | TFLOPs: 6.46 | +31: iteration 21500/ 37905 | consumed samples: 5504000 | consumed tokens: 11272192000 | elapsed time per iteration (s): 0.20 | learning rate: 9.114E-05 | global batch size: 256 | lm loss: 2.937034E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.603 | TFLOPs: 8.09 | +31: iteration 21510/ 37905 | consumed samples: 5506560 | consumed tokens: 11277434880 | elapsed time per iteration (s): 0.21 | learning rate: 9.107E-05 | global batch size: 256 | lm loss: 2.896750E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.759 | TFLOPs: 7.86 | +31: iteration 21520/ 37905 | consumed samples: 5509120 | consumed tokens: 11282677760 | elapsed time per iteration (s): 0.21 | learning rate: 9.099E-05 | global batch size: 256 | lm loss: 2.946501E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.452 | TFLOPs: 7.86 | +31: iteration 21530/ 37905 | consumed samples: 5511680 | consumed tokens: 11287920640 | elapsed time per iteration (s): 0.20 | learning rate: 9.092E-05 | global batch size: 256 | lm loss: 2.903895E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.674 | TFLOPs: 8.33 | +31: iteration 21540/ 37905 | consumed samples: 5514240 | consumed tokens: 11293163520 | elapsed time per iteration (s): 0.22 | learning rate: 9.085E-05 | global batch size: 256 | lm loss: 2.884826E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.908 | TFLOPs: 7.35 | +31: iteration 21550/ 37905 | consumed samples: 5516800 | consumed tokens: 11298406400 | elapsed time per iteration (s): 0.24 | learning rate: 9.077E-05 | global batch size: 256 | lm loss: 2.950030E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.318 | TFLOPs: 6.87 | +31: iteration 21560/ 37905 | consumed samples: 5519360 | consumed tokens: 11303649280 | elapsed time per iteration (s): 0.24 | learning rate: 9.070E-05 | global batch size: 256 | lm loss: 2.921397E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.791 | TFLOPs: 6.74 | +31: iteration 21570/ 37905 | consumed samples: 5521920 | consumed tokens: 11308892160 | elapsed time per iteration (s): 0.23 | learning rate: 9.063E-05 | global batch size: 256 | lm loss: 2.920615E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.673 | TFLOPs: 7.16 | +31: iteration 21580/ 37905 | consumed samples: 5524480 | consumed tokens: 11314135040 | elapsed time per iteration (s): 0.22 | learning rate: 9.056E-05 | global batch size: 256 | lm loss: 2.933787E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.301 | TFLOPs: 7.35 | +31: iteration 21590/ 37905 | consumed samples: 5527040 | consumed tokens: 11319377920 | elapsed time per iteration (s): 0.28 | learning rate: 9.048E-05 | global batch size: 256 | lm loss: 2.889649E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 929.033 | TFLOPs: 5.92 | +31: iteration 21600/ 37905 | consumed samples: 5529600 | consumed tokens: 11324620800 | elapsed time per iteration (s): 0.26 | learning rate: 9.041E-05 | global batch size: 256 | lm loss: 2.945800E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.394 | TFLOPs: 6.33 | +31: iteration 21610/ 37905 | consumed samples: 5532160 | consumed tokens: 11329863680 | elapsed time per iteration (s): 0.22 | learning rate: 9.034E-05 | global batch size: 256 | lm loss: 2.961883E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.465 | TFLOPs: 7.25 | +31: iteration 21620/ 37905 | consumed samples: 5534720 | consumed tokens: 11335106560 | elapsed time per iteration (s): 0.22 | learning rate: 9.026E-05 | global batch size: 256 | lm loss: 2.949538E+00 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.503 | TFLOPs: 7.26 | +31: iteration 21630/ 37905 | consumed samples: 5537280 | consumed tokens: 11340349440 | elapsed time per iteration (s): 0.20 | learning rate: 9.019E-05 | global batch size: 256 | lm loss: 2.961887E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.218 | TFLOPs: 8.09 | +31: iteration 21640/ 37905 | consumed samples: 5539840 | consumed tokens: 11345592320 | elapsed time per iteration (s): 0.23 | learning rate: 9.012E-05 | global batch size: 256 | lm loss: 2.952386E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.337 | TFLOPs: 7.06 | +31: iteration 21650/ 37905 | consumed samples: 5542400 | consumed tokens: 11350835200 | elapsed time per iteration (s): 0.21 | learning rate: 9.005E-05 | global batch size: 256 | lm loss: 2.922680E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.321 | TFLOPs: 7.75 | +31: iteration 21660/ 37905 | consumed samples: 5544960 | consumed tokens: 11356078080 | elapsed time per iteration (s): 0.23 | learning rate: 8.997E-05 | global batch size: 256 | lm loss: 2.937035E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.274 | TFLOPs: 7.17 | +31: iteration 21670/ 37905 | consumed samples: 5547520 | consumed tokens: 11361320960 | elapsed time per iteration (s): 0.22 | learning rate: 8.990E-05 | global batch size: 256 | lm loss: 2.885279E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.508 | TFLOPs: 7.58 | +31: iteration 21680/ 37905 | consumed samples: 5550080 | consumed tokens: 11366563840 | elapsed time per iteration (s): 0.23 | learning rate: 8.983E-05 | global batch size: 256 | lm loss: 2.942082E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.012 | TFLOPs: 7.02 | +31: iteration 21690/ 37905 | consumed samples: 5552640 | consumed tokens: 11371806720 | elapsed time per iteration (s): 0.20 | learning rate: 8.976E-05 | global batch size: 256 | lm loss: 2.908285E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.337 | TFLOPs: 7.98 | +31: iteration 21700/ 37905 | consumed samples: 5555200 | consumed tokens: 11377049600 | elapsed time per iteration (s): 0.20 | learning rate: 8.968E-05 | global batch size: 256 | lm loss: 2.894637E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.536 | TFLOPs: 8.19 | +31: iteration 21710/ 37905 | consumed samples: 5557760 | consumed tokens: 11382292480 | elapsed time per iteration (s): 0.20 | learning rate: 8.961E-05 | global batch size: 256 | lm loss: 2.918970E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1257.778 | TFLOPs: 8.01 | +31: iteration 21720/ 37905 | consumed samples: 5560320 | consumed tokens: 11387535360 | elapsed time per iteration (s): 0.22 | learning rate: 8.954E-05 | global batch size: 256 | lm loss: 2.925648E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.734 | TFLOPs: 7.44 | +31: iteration 21730/ 37905 | consumed samples: 5562880 | consumed tokens: 11392778240 | elapsed time per iteration (s): 0.23 | learning rate: 8.946E-05 | global batch size: 256 | lm loss: 2.911470E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1092.076 | TFLOPs: 6.96 | +31: iteration 21740/ 37905 | consumed samples: 5565440 | consumed tokens: 11398021120 | elapsed time per iteration (s): 0.21 | learning rate: 8.939E-05 | global batch size: 256 | lm loss: 2.901762E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.333 | TFLOPs: 7.66 | +31: iteration 21750/ 37905 | consumed samples: 5568000 | consumed tokens: 11403264000 | elapsed time per iteration (s): 0.22 | learning rate: 8.932E-05 | global batch size: 256 | lm loss: 2.919881E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.785 | TFLOPs: 7.32 | +31: iteration 21760/ 37905 | consumed samples: 5570560 | consumed tokens: 11408506880 | elapsed time per iteration (s): 0.20 | learning rate: 8.925E-05 | global batch size: 256 | lm loss: 2.947770E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.791 | TFLOPs: 8.06 | +31: iteration 21770/ 37905 | consumed samples: 5573120 | consumed tokens: 11413749760 | elapsed time per iteration (s): 0.19 | learning rate: 8.917E-05 | global batch size: 256 | lm loss: 2.928204E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.357 | TFLOPs: 8.41 | +31: iteration 21780/ 37905 | consumed samples: 5575680 | consumed tokens: 11418992640 | elapsed time per iteration (s): 0.22 | learning rate: 8.910E-05 | global batch size: 256 | lm loss: 2.912100E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.481 | TFLOPs: 7.54 | +31: iteration 21790/ 37905 | consumed samples: 5578240 | consumed tokens: 11424235520 | elapsed time per iteration (s): 0.22 | learning rate: 8.903E-05 | global batch size: 256 | lm loss: 2.936650E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.316 | TFLOPs: 7.57 | +31: iteration 21800/ 37905 | consumed samples: 5580800 | consumed tokens: 11429478400 | elapsed time per iteration (s): 0.22 | learning rate: 8.896E-05 | global batch size: 256 | lm loss: 2.937092E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.850 | TFLOPs: 7.48 | +31: iteration 21810/ 37905 | consumed samples: 5583360 | consumed tokens: 11434721280 | elapsed time per iteration (s): 0.21 | learning rate: 8.888E-05 | global batch size: 256 | lm loss: 2.923712E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.994 | TFLOPs: 7.65 | +31: iteration 21820/ 37905 | consumed samples: 5585920 | consumed tokens: 11439964160 | elapsed time per iteration (s): 0.20 | learning rate: 8.881E-05 | global batch size: 256 | lm loss: 2.933236E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.099 | TFLOPs: 7.96 | +31: iteration 21830/ 37905 | consumed samples: 5588480 | consumed tokens: 11445207040 | elapsed time per iteration (s): 0.20 | learning rate: 8.874E-05 | global batch size: 256 | lm loss: 2.942601E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.741 | TFLOPs: 8.07 | +31: iteration 21840/ 37905 | consumed samples: 5591040 | consumed tokens: 11450449920 | elapsed time per iteration (s): 0.20 | learning rate: 8.867E-05 | global batch size: 256 | lm loss: 2.936086E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1298.216 | TFLOPs: 8.27 | +31: iteration 21850/ 37905 | consumed samples: 5593600 | consumed tokens: 11455692800 | elapsed time per iteration (s): 0.20 | learning rate: 8.859E-05 | global batch size: 256 | lm loss: 2.958641E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.894 | TFLOPs: 8.10 | +31: iteration 21860/ 37905 | consumed samples: 5596160 | consumed tokens: 11460935680 | elapsed time per iteration (s): 0.22 | learning rate: 8.852E-05 | global batch size: 256 | lm loss: 2.958749E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.269 | TFLOPs: 7.49 | +31: iteration 21870/ 37905 | consumed samples: 5598720 | consumed tokens: 11466178560 | elapsed time per iteration (s): 0.21 | learning rate: 8.845E-05 | global batch size: 256 | lm loss: 2.955854E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.168 | TFLOPs: 7.62 | +31: iteration 21880/ 37905 | consumed samples: 5601280 | consumed tokens: 11471421440 | elapsed time per iteration (s): 0.21 | learning rate: 8.838E-05 | global batch size: 256 | lm loss: 2.914184E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.559 | TFLOPs: 7.83 | +31: iteration 21890/ 37905 | consumed samples: 5603840 | consumed tokens: 11476664320 | elapsed time per iteration (s): 0.19 | learning rate: 8.830E-05 | global batch size: 256 | lm loss: 2.907057E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1348.210 | TFLOPs: 8.59 | +31: iteration 21900/ 37905 | consumed samples: 5606400 | consumed tokens: 11481907200 | elapsed time per iteration (s): 0.21 | learning rate: 8.823E-05 | global batch size: 256 | lm loss: 2.954150E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.704 | TFLOPs: 7.60 | +31: iteration 21910/ 37905 | consumed samples: 5608960 | consumed tokens: 11487150080 | elapsed time per iteration (s): 0.21 | learning rate: 8.816E-05 | global batch size: 256 | lm loss: 2.942785E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.084 | TFLOPs: 7.86 | +31: iteration 21920/ 37905 | consumed samples: 5611520 | consumed tokens: 11492392960 | elapsed time per iteration (s): 0.22 | learning rate: 8.809E-05 | global batch size: 256 | lm loss: 2.908344E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.704 | TFLOPs: 7.49 | +31: iteration 21930/ 37905 | consumed samples: 5614080 | consumed tokens: 11497635840 | elapsed time per iteration (s): 0.22 | learning rate: 8.802E-05 | global batch size: 256 | lm loss: 2.910254E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.415 | TFLOPs: 7.44 | +31: iteration 21940/ 37905 | consumed samples: 5616640 | consumed tokens: 11502878720 | elapsed time per iteration (s): 0.22 | learning rate: 8.794E-05 | global batch size: 256 | lm loss: 2.962051E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.151 | TFLOPs: 7.43 | +31: iteration 21950/ 37905 | consumed samples: 5619200 | consumed tokens: 11508121600 | elapsed time per iteration (s): 0.20 | learning rate: 8.787E-05 | global batch size: 256 | lm loss: 2.962670E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.355 | TFLOPs: 8.09 | +31: iteration 21960/ 37905 | consumed samples: 5621760 | consumed tokens: 11513364480 | elapsed time per iteration (s): 0.23 | learning rate: 8.780E-05 | global batch size: 256 | lm loss: 2.951866E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.847 | TFLOPs: 7.09 | +31: iteration 21970/ 37905 | consumed samples: 5624320 | consumed tokens: 11518607360 | elapsed time per iteration (s): 0.24 | learning rate: 8.773E-05 | global batch size: 256 | lm loss: 2.942609E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.068 | TFLOPs: 6.78 | +31: iteration 21980/ 37905 | consumed samples: 5626880 | consumed tokens: 11523850240 | elapsed time per iteration (s): 0.22 | learning rate: 8.765E-05 | global batch size: 256 | lm loss: 2.920408E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.974 | TFLOPs: 7.30 | +31: iteration 21990/ 37905 | consumed samples: 5629440 | consumed tokens: 11529093120 | elapsed time per iteration (s): 0.22 | learning rate: 8.758E-05 | global batch size: 256 | lm loss: 2.968894E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.730 | TFLOPs: 7.49 | + 0: [2022-11-24 15:30:41,113] [INFO] [logging.py:68:log_dist] [Rank 0] step=22000, skipped=0, lr=[8.750917535429743e-05, 8.750917535429743e-05, 8.750917535429743e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 22000/ 37905 | consumed samples: 5632000 | consumed tokens: 11534336000 | elapsed time per iteration (s): 0.22 | learning rate: 8.751E-05 | global batch size: 256 | lm loss: 2.916270E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.991 | TFLOPs: 7.34 | + 0: steps: 22000 loss: 2.9027 iter time (s): 0.219 samples/sec: 1171.165 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 22000 | lm loss value: 2.814891E+00 | lm loss PPL: 1.669135E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 22000 to checkpoints_83m + 0: [2022-11-24 15:30:41,220] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step22000 is begin to save! + 0: [2022-11-24 15:30:41,230] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,314] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,327] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,339] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,363] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,374] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,399] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,411] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,423] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,436] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,436] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:30:41,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:30:41,438] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step22000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:30:41,438] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:30:41,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:30:41,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step22000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:30:41,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +10: [2022-11-24 15:30:41,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +15: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +16: [2022-11-24 15:30:41,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +16: [2022-11-24 15:30:41,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:30:41,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +30: [2022-11-24 15:30:41,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:30:41,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +24: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +24: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 7: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 5: [2022-11-24 15:30:41,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +10: [2022-11-24 15:30:41,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +29: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:30:41,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:30:41,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +22: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:30:41,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +17: [2022-11-24 15:30:41,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,518] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,518] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:30:41,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,519] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +16: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +15: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +13: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,520] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,520] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:30:41,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +14: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +28: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +14: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +30: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,521] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:30:41,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,522] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,522] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 1: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:30:41,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +24: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,523] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,523] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +18: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:30:41,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +18: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 5: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,524] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,524] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,525] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:30:41,525] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:30:41,525] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,525] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +22: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,525] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:30:41,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:30:41,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:30:41,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 4: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,526] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +15: [2022-11-24 15:30:41,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +13: [2022-11-24 15:30:41,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +28: [2022-11-24 15:30:41,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +14: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:30:41,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +30: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:30:41,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 1: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:30:41,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +24: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +18: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +18: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 5: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 7: [2022-11-24 15:30:41,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:30:41,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:30:41,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:30:41,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +29: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:30:41,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:30:41,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +22: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:30:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 4: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 4: [2022-11-24 15:30:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +16: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +13: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:30:41,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +14: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +30: [2022-11-24 15:30:41,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:30:41,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +27: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 1: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +18: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +24: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:30:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 5: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +10: [2022-11-24 15:30:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 7: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:30:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:30:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +29: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:30:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:30:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +22: [2022-11-24 15:30:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +22: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 4: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +22: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:30:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +15: [2022-11-24 15:30:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +13: [2022-11-24 15:30:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +16: [2022-11-24 15:30:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +14: [2022-11-24 15:30:41,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:30:41,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +30: [2022-11-24 15:30:41,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:30:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 1: [2022-11-24 15:30:41,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:30:41,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +18: [2022-11-24 15:30:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +24: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:30:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 7: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 7: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:30:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +17: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +29: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:30:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:30:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:30:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:30:41,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +15: [2022-11-24 15:30:41,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +16: [2022-11-24 15:30:41,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +13: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +14: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:30:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +30: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:30:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 1: [2022-11-24 15:30:41,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:30:41,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:30:41,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:30:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +24: [2022-11-24 15:30:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +18: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +18: [2022-11-24 15:30:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:30:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 5: [2022-11-24 15:30:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 7: [2022-11-24 15:30:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:30:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:30:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:30:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +29: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:30:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +22: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +12: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:30:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +10: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +15: [2022-11-24 15:30:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:30:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +22: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +13: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +30: [2022-11-24 15:30:41,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:30:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 1: [2022-11-24 15:30:41,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:30:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:30:41,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:30:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 6: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +18: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +25: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +25: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +24: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +21: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +15: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +24: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +15: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +21: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +11: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +11: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 5: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +16: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +22: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +22: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 2: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 3: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 4: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +31: [2022-11-24 15:30:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:30:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 4: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +12: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +31: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +26: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +23: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +17: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +14: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +26: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +24: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +23: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +18: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +17: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +28: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +14: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +24: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 7: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +18: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +17: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +29: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 4: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +28: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +13: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +18: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +20: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +29: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +29: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +13: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +20: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:30:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 8: [2022-11-24 15:30:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:30:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +27: [2022-11-24 15:30:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +19: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! +10: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:30:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:30:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 9: [2022-11-24 15:30:41,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:30:41,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step22000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:30:41,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step22000 is ready now! + 0: successfully saved checkpoint at iteration 22000 to checkpoints_83m +31: time (ms) | save-checkpoint: 349.03 +31: iteration 22010/ 37905 | consumed samples: 5634560 | consumed tokens: 11539578880 | elapsed time per iteration (s): 0.31 | learning rate: 8.744E-05 | global batch size: 256 | lm loss: 2.932213E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 836.447 | TFLOPs: 5.33 | +31: iteration 22020/ 37905 | consumed samples: 5637120 | consumed tokens: 11544821760 | elapsed time per iteration (s): 0.22 | learning rate: 8.736E-05 | global batch size: 256 | lm loss: 2.928088E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.076 | TFLOPs: 7.45 | +31: iteration 22030/ 37905 | consumed samples: 5639680 | consumed tokens: 11550064640 | elapsed time per iteration (s): 0.21 | learning rate: 8.729E-05 | global batch size: 256 | lm loss: 2.937009E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.710 | TFLOPs: 7.60 | +31: iteration 22040/ 37905 | consumed samples: 5642240 | consumed tokens: 11555307520 | elapsed time per iteration (s): 0.23 | learning rate: 8.722E-05 | global batch size: 256 | lm loss: 2.889480E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.156 | TFLOPs: 7.17 | +31: iteration 22050/ 37905 | consumed samples: 5644800 | consumed tokens: 11560550400 | elapsed time per iteration (s): 0.20 | learning rate: 8.715E-05 | global batch size: 256 | lm loss: 2.916309E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.861 | TFLOPs: 8.17 | +31: iteration 22060/ 37905 | consumed samples: 5647360 | consumed tokens: 11565793280 | elapsed time per iteration (s): 0.22 | learning rate: 8.708E-05 | global batch size: 256 | lm loss: 2.928818E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1188.869 | TFLOPs: 7.57 | +31: iteration 22070/ 37905 | consumed samples: 5649920 | consumed tokens: 11571036160 | elapsed time per iteration (s): 0.22 | learning rate: 8.700E-05 | global batch size: 256 | lm loss: 2.907927E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.859 | TFLOPs: 7.56 | +31: iteration 22080/ 37905 | consumed samples: 5652480 | consumed tokens: 11576279040 | elapsed time per iteration (s): 0.21 | learning rate: 8.693E-05 | global batch size: 256 | lm loss: 2.945174E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.507 | TFLOPs: 7.66 | +31: iteration 22090/ 37905 | consumed samples: 5655040 | consumed tokens: 11581521920 | elapsed time per iteration (s): 0.20 | learning rate: 8.686E-05 | global batch size: 256 | lm loss: 2.949430E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.866 | TFLOPs: 7.97 | +31: iteration 22100/ 37905 | consumed samples: 5657600 | consumed tokens: 11586764800 | elapsed time per iteration (s): 0.26 | learning rate: 8.679E-05 | global batch size: 256 | lm loss: 2.940042E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 997.322 | TFLOPs: 6.35 | +31: iteration 22110/ 37905 | consumed samples: 5660160 | consumed tokens: 11592007680 | elapsed time per iteration (s): 0.23 | learning rate: 8.672E-05 | global batch size: 256 | lm loss: 2.945134E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.775 | TFLOPs: 7.09 | +31: iteration 22120/ 37905 | consumed samples: 5662720 | consumed tokens: 11597250560 | elapsed time per iteration (s): 0.22 | learning rate: 8.664E-05 | global batch size: 256 | lm loss: 2.934677E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.472 | TFLOPs: 7.56 | +31: iteration 22130/ 37905 | consumed samples: 5665280 | consumed tokens: 11602493440 | elapsed time per iteration (s): 0.23 | learning rate: 8.657E-05 | global batch size: 256 | lm loss: 2.951394E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.437 | TFLOPs: 7.22 | +31: iteration 22140/ 37905 | consumed samples: 5667840 | consumed tokens: 11607736320 | elapsed time per iteration (s): 0.20 | learning rate: 8.650E-05 | global batch size: 256 | lm loss: 2.889525E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.294 | TFLOPs: 8.12 | +31: iteration 22150/ 37905 | consumed samples: 5670400 | consumed tokens: 11612979200 | elapsed time per iteration (s): 0.24 | learning rate: 8.643E-05 | global batch size: 256 | lm loss: 2.920405E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.167 | TFLOPs: 6.68 | +31: iteration 22160/ 37905 | consumed samples: 5672960 | consumed tokens: 11618222080 | elapsed time per iteration (s): 0.19 | learning rate: 8.636E-05 | global batch size: 256 | lm loss: 2.956885E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1322.145 | TFLOPs: 8.42 | +31: iteration 22170/ 37905 | consumed samples: 5675520 | consumed tokens: 11623464960 | elapsed time per iteration (s): 0.23 | learning rate: 8.628E-05 | global batch size: 256 | lm loss: 2.902344E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.994 | TFLOPs: 7.07 | +31: iteration 22180/ 37905 | consumed samples: 5678080 | consumed tokens: 11628707840 | elapsed time per iteration (s): 0.20 | learning rate: 8.621E-05 | global batch size: 256 | lm loss: 2.944472E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.497 | TFLOPs: 7.99 | +31: iteration 22190/ 37905 | consumed samples: 5680640 | consumed tokens: 11633950720 | elapsed time per iteration (s): 0.20 | learning rate: 8.614E-05 | global batch size: 256 | lm loss: 2.952952E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.686 | TFLOPs: 7.98 | +31: iteration 22200/ 37905 | consumed samples: 5683200 | consumed tokens: 11639193600 | elapsed time per iteration (s): 0.24 | learning rate: 8.607E-05 | global batch size: 256 | lm loss: 2.927231E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.464 | TFLOPs: 6.84 | +31: iteration 22210/ 37905 | consumed samples: 5685760 | consumed tokens: 11644436480 | elapsed time per iteration (s): 0.22 | learning rate: 8.600E-05 | global batch size: 256 | lm loss: 2.946301E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.901 | TFLOPs: 7.51 | +31: iteration 22220/ 37905 | consumed samples: 5688320 | consumed tokens: 11649679360 | elapsed time per iteration (s): 0.21 | learning rate: 8.592E-05 | global batch size: 256 | lm loss: 2.924628E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1214.373 | TFLOPs: 7.73 | +31: iteration 22230/ 37905 | consumed samples: 5690880 | consumed tokens: 11654922240 | elapsed time per iteration (s): 0.22 | learning rate: 8.585E-05 | global batch size: 256 | lm loss: 2.955323E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1180.796 | TFLOPs: 7.52 | +31: iteration 22240/ 37905 | consumed samples: 5693440 | consumed tokens: 11660165120 | elapsed time per iteration (s): 0.23 | learning rate: 8.578E-05 | global batch size: 256 | lm loss: 2.953902E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.599 | TFLOPs: 7.04 | +31: iteration 22250/ 37905 | consumed samples: 5696000 | consumed tokens: 11665408000 | elapsed time per iteration (s): 0.24 | learning rate: 8.571E-05 | global batch size: 256 | lm loss: 2.886935E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.868 | TFLOPs: 6.88 | +31: iteration 22260/ 37905 | consumed samples: 5698560 | consumed tokens: 11670650880 | elapsed time per iteration (s): 0.20 | learning rate: 8.564E-05 | global batch size: 256 | lm loss: 2.934320E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.325 | TFLOPs: 8.15 | +31: iteration 22270/ 37905 | consumed samples: 5701120 | consumed tokens: 11675893760 | elapsed time per iteration (s): 0.24 | learning rate: 8.556E-05 | global batch size: 256 | lm loss: 2.957378E+00 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.120 | TFLOPs: 6.85 | +31: iteration 22280/ 37905 | consumed samples: 5703680 | consumed tokens: 11681136640 | elapsed time per iteration (s): 0.22 | learning rate: 8.549E-05 | global batch size: 256 | lm loss: 2.947532E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.033 | TFLOPs: 7.44 | +31: iteration 22290/ 37905 | consumed samples: 5706240 | consumed tokens: 11686379520 | elapsed time per iteration (s): 0.22 | learning rate: 8.542E-05 | global batch size: 256 | lm loss: 2.985485E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1155.271 | TFLOPs: 7.36 | +31: iteration 22300/ 37905 | consumed samples: 5708800 | consumed tokens: 11691622400 | elapsed time per iteration (s): 0.23 | learning rate: 8.535E-05 | global batch size: 256 | lm loss: 2.914527E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.475 | TFLOPs: 6.95 | +31: iteration 22310/ 37905 | consumed samples: 5711360 | consumed tokens: 11696865280 | elapsed time per iteration (s): 0.23 | learning rate: 8.528E-05 | global batch size: 256 | lm loss: 2.928944E+00 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.655 | TFLOPs: 7.02 | +31: iteration 22320/ 37905 | consumed samples: 5713920 | consumed tokens: 11702108160 | elapsed time per iteration (s): 0.21 | learning rate: 8.521E-05 | global batch size: 256 | lm loss: 2.905949E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.697 | TFLOPs: 7.90 | +31: iteration 22330/ 37905 | consumed samples: 5716480 | consumed tokens: 11707351040 | elapsed time per iteration (s): 0.21 | learning rate: 8.513E-05 | global batch size: 256 | lm loss: 2.934228E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.415 | TFLOPs: 7.85 | +31: iteration 22340/ 37905 | consumed samples: 5719040 | consumed tokens: 11712593920 | elapsed time per iteration (s): 0.25 | learning rate: 8.506E-05 | global batch size: 256 | lm loss: 2.910148E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1024.800 | TFLOPs: 6.53 | +31: iteration 22350/ 37905 | consumed samples: 5721600 | consumed tokens: 11717836800 | elapsed time per iteration (s): 0.20 | learning rate: 8.499E-05 | global batch size: 256 | lm loss: 2.882913E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.304 | TFLOPs: 7.99 | +31: iteration 22360/ 37905 | consumed samples: 5724160 | consumed tokens: 11723079680 | elapsed time per iteration (s): 0.21 | learning rate: 8.492E-05 | global batch size: 256 | lm loss: 2.934559E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.077 | TFLOPs: 7.87 | +31: iteration 22370/ 37905 | consumed samples: 5726720 | consumed tokens: 11728322560 | elapsed time per iteration (s): 0.24 | learning rate: 8.485E-05 | global batch size: 256 | lm loss: 2.914813E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.171 | TFLOPs: 6.81 | +31: iteration 22380/ 37905 | consumed samples: 5729280 | consumed tokens: 11733565440 | elapsed time per iteration (s): 0.22 | learning rate: 8.478E-05 | global batch size: 256 | lm loss: 2.912638E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.779 | TFLOPs: 7.50 | +31: iteration 22390/ 37905 | consumed samples: 5731840 | consumed tokens: 11738808320 | elapsed time per iteration (s): 0.18 | learning rate: 8.470E-05 | global batch size: 256 | lm loss: 2.867947E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1410.350 | TFLOPs: 8.98 | +31: iteration 22400/ 37905 | consumed samples: 5734400 | consumed tokens: 11744051200 | elapsed time per iteration (s): 0.20 | learning rate: 8.463E-05 | global batch size: 256 | lm loss: 2.915549E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1297.507 | TFLOPs: 8.26 | +31: iteration 22410/ 37905 | consumed samples: 5736960 | consumed tokens: 11749294080 | elapsed time per iteration (s): 0.20 | learning rate: 8.456E-05 | global batch size: 256 | lm loss: 2.916160E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.975 | TFLOPs: 8.05 | +31: iteration 22420/ 37905 | consumed samples: 5739520 | consumed tokens: 11754536960 | elapsed time per iteration (s): 0.21 | learning rate: 8.449E-05 | global batch size: 256 | lm loss: 2.897618E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.046 | TFLOPs: 7.80 | +31: iteration 22430/ 37905 | consumed samples: 5742080 | consumed tokens: 11759779840 | elapsed time per iteration (s): 0.24 | learning rate: 8.442E-05 | global batch size: 256 | lm loss: 2.891074E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.760 | TFLOPs: 6.91 | +31: iteration 22440/ 37905 | consumed samples: 5744640 | consumed tokens: 11765022720 | elapsed time per iteration (s): 0.20 | learning rate: 8.435E-05 | global batch size: 256 | lm loss: 2.926513E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.825 | TFLOPs: 8.11 | +31: iteration 22450/ 37905 | consumed samples: 5747200 | consumed tokens: 11770265600 | elapsed time per iteration (s): 0.22 | learning rate: 8.428E-05 | global batch size: 256 | lm loss: 2.942113E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.568 | TFLOPs: 7.46 | +31: iteration 22460/ 37905 | consumed samples: 5749760 | consumed tokens: 11775508480 | elapsed time per iteration (s): 0.21 | learning rate: 8.420E-05 | global batch size: 256 | lm loss: 2.945183E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.406 | TFLOPs: 7.66 | +31: iteration 22470/ 37905 | consumed samples: 5752320 | consumed tokens: 11780751360 | elapsed time per iteration (s): 0.21 | learning rate: 8.413E-05 | global batch size: 256 | lm loss: 2.944295E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.064 | TFLOPs: 7.60 | +31: iteration 22480/ 37905 | consumed samples: 5754880 | consumed tokens: 11785994240 | elapsed time per iteration (s): 0.22 | learning rate: 8.406E-05 | global batch size: 256 | lm loss: 2.909508E+00 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1188.384 | TFLOPs: 7.57 | +31: iteration 22490/ 37905 | consumed samples: 5757440 | consumed tokens: 11791237120 | elapsed time per iteration (s): 0.25 | learning rate: 8.399E-05 | global batch size: 256 | lm loss: 2.897898E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.268 | TFLOPs: 6.64 | +31: iteration 22500/ 37905 | consumed samples: 5760000 | consumed tokens: 11796480000 | elapsed time per iteration (s): 0.24 | learning rate: 8.392E-05 | global batch size: 256 | lm loss: 2.927057E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.107 | TFLOPs: 6.74 | +31: iteration 22510/ 37905 | consumed samples: 5762560 | consumed tokens: 11801722880 | elapsed time per iteration (s): 0.22 | learning rate: 8.385E-05 | global batch size: 256 | lm loss: 2.942009E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.151 | TFLOPs: 7.40 | +31: iteration 22520/ 37905 | consumed samples: 5765120 | consumed tokens: 11806965760 | elapsed time per iteration (s): 0.20 | learning rate: 8.378E-05 | global batch size: 256 | lm loss: 2.935338E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.346 | TFLOPs: 8.05 | +31: iteration 22530/ 37905 | consumed samples: 5767680 | consumed tokens: 11812208640 | elapsed time per iteration (s): 0.22 | learning rate: 8.370E-05 | global batch size: 256 | lm loss: 2.946547E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.373 | TFLOPs: 7.37 | +31: iteration 22540/ 37905 | consumed samples: 5770240 | consumed tokens: 11817451520 | elapsed time per iteration (s): 0.21 | learning rate: 8.363E-05 | global batch size: 256 | lm loss: 2.929408E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.313 | TFLOPs: 7.84 | +31: iteration 22550/ 37905 | consumed samples: 5772800 | consumed tokens: 11822694400 | elapsed time per iteration (s): 0.23 | learning rate: 8.356E-05 | global batch size: 256 | lm loss: 2.960824E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.416 | TFLOPs: 7.00 | +31: iteration 22560/ 37905 | consumed samples: 5775360 | consumed tokens: 11827937280 | elapsed time per iteration (s): 0.20 | learning rate: 8.349E-05 | global batch size: 256 | lm loss: 2.915188E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.253 | TFLOPs: 8.10 | +31: iteration 22570/ 37905 | consumed samples: 5777920 | consumed tokens: 11833180160 | elapsed time per iteration (s): 0.20 | learning rate: 8.342E-05 | global batch size: 256 | lm loss: 2.916904E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.100 | TFLOPs: 7.98 | +31: iteration 22580/ 37905 | consumed samples: 5780480 | consumed tokens: 11838423040 | elapsed time per iteration (s): 0.25 | learning rate: 8.335E-05 | global batch size: 256 | lm loss: 2.902595E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.605 | TFLOPs: 6.60 | +31: iteration 22590/ 37905 | consumed samples: 5783040 | consumed tokens: 11843665920 | elapsed time per iteration (s): 0.23 | learning rate: 8.328E-05 | global batch size: 256 | lm loss: 2.923450E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.708 | TFLOPs: 7.04 | +31: iteration 22600/ 37905 | consumed samples: 5785600 | consumed tokens: 11848908800 | elapsed time per iteration (s): 0.26 | learning rate: 8.321E-05 | global batch size: 256 | lm loss: 2.927844E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.934 | TFLOPs: 6.35 | +31: iteration 22610/ 37905 | consumed samples: 5788160 | consumed tokens: 11854151680 | elapsed time per iteration (s): 0.21 | learning rate: 8.313E-05 | global batch size: 256 | lm loss: 2.911150E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.349 | TFLOPs: 7.63 | +31: iteration 22620/ 37905 | consumed samples: 5790720 | consumed tokens: 11859394560 | elapsed time per iteration (s): 0.21 | learning rate: 8.306E-05 | global batch size: 256 | lm loss: 2.920263E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.309 | TFLOPs: 7.79 | +31: iteration 22630/ 37905 | consumed samples: 5793280 | consumed tokens: 11864637440 | elapsed time per iteration (s): 0.23 | learning rate: 8.299E-05 | global batch size: 256 | lm loss: 2.953965E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.519 | TFLOPs: 7.19 | +31: iteration 22640/ 37905 | consumed samples: 5795840 | consumed tokens: 11869880320 | elapsed time per iteration (s): 0.21 | learning rate: 8.292E-05 | global batch size: 256 | lm loss: 2.908622E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.814 | TFLOPs: 7.64 | +31: iteration 22650/ 37905 | consumed samples: 5798400 | consumed tokens: 11875123200 | elapsed time per iteration (s): 0.23 | learning rate: 8.285E-05 | global batch size: 256 | lm loss: 2.927160E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.325 | TFLOPs: 7.15 | +31: iteration 22660/ 37905 | consumed samples: 5800960 | consumed tokens: 11880366080 | elapsed time per iteration (s): 0.23 | learning rate: 8.278E-05 | global batch size: 256 | lm loss: 2.921088E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.959 | TFLOPs: 7.15 | +31: iteration 22670/ 37905 | consumed samples: 5803520 | consumed tokens: 11885608960 | elapsed time per iteration (s): 0.26 | learning rate: 8.271E-05 | global batch size: 256 | lm loss: 2.911638E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.762 | TFLOPs: 6.32 | +31: iteration 22680/ 37905 | consumed samples: 5806080 | consumed tokens: 11890851840 | elapsed time per iteration (s): 0.21 | learning rate: 8.264E-05 | global batch size: 256 | lm loss: 2.935224E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1208.433 | TFLOPs: 7.70 | +31: iteration 22690/ 37905 | consumed samples: 5808640 | consumed tokens: 11896094720 | elapsed time per iteration (s): 0.23 | learning rate: 8.257E-05 | global batch size: 256 | lm loss: 2.956042E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.523 | TFLOPs: 7.21 | +31: iteration 22700/ 37905 | consumed samples: 5811200 | consumed tokens: 11901337600 | elapsed time per iteration (s): 0.22 | learning rate: 8.249E-05 | global batch size: 256 | lm loss: 2.922736E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.489 | TFLOPs: 7.37 | +31: iteration 22710/ 37905 | consumed samples: 5813760 | consumed tokens: 11906580480 | elapsed time per iteration (s): 0.23 | learning rate: 8.242E-05 | global batch size: 256 | lm loss: 2.958174E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.154 | TFLOPs: 7.17 | +31: iteration 22720/ 37905 | consumed samples: 5816320 | consumed tokens: 11911823360 | elapsed time per iteration (s): 0.23 | learning rate: 8.235E-05 | global batch size: 256 | lm loss: 2.907269E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.949 | TFLOPs: 7.14 | +31: iteration 22730/ 37905 | consumed samples: 5818880 | consumed tokens: 11917066240 | elapsed time per iteration (s): 0.21 | learning rate: 8.228E-05 | global batch size: 256 | lm loss: 2.900860E+00 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.187 | TFLOPs: 7.66 | +31: iteration 22740/ 37905 | consumed samples: 5821440 | consumed tokens: 11922309120 | elapsed time per iteration (s): 0.25 | learning rate: 8.221E-05 | global batch size: 256 | lm loss: 2.907010E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.150 | TFLOPs: 6.63 | +31: iteration 22750/ 37905 | consumed samples: 5824000 | consumed tokens: 11927552000 | elapsed time per iteration (s): 0.23 | learning rate: 8.214E-05 | global batch size: 256 | lm loss: 2.892755E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.315 | TFLOPs: 7.03 | +31: iteration 22760/ 37905 | consumed samples: 5826560 | consumed tokens: 11932794880 | elapsed time per iteration (s): 0.26 | learning rate: 8.207E-05 | global batch size: 256 | lm loss: 2.965576E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.752 | TFLOPs: 6.37 | +31: iteration 22770/ 37905 | consumed samples: 5829120 | consumed tokens: 11938037760 | elapsed time per iteration (s): 0.25 | learning rate: 8.200E-05 | global batch size: 256 | lm loss: 2.933031E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.023 | TFLOPs: 6.44 | +31: iteration 22780/ 37905 | consumed samples: 5831680 | consumed tokens: 11943280640 | elapsed time per iteration (s): 0.24 | learning rate: 8.193E-05 | global batch size: 256 | lm loss: 2.940761E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.921 | TFLOPs: 6.92 | +31: iteration 22790/ 37905 | consumed samples: 5834240 | consumed tokens: 11948523520 | elapsed time per iteration (s): 0.22 | learning rate: 8.186E-05 | global batch size: 256 | lm loss: 2.951676E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.031 | TFLOPs: 7.39 | +31: iteration 22800/ 37905 | consumed samples: 5836800 | consumed tokens: 11953766400 | elapsed time per iteration (s): 0.23 | learning rate: 8.178E-05 | global batch size: 256 | lm loss: 2.924018E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.542 | TFLOPs: 7.07 | +31: iteration 22810/ 37905 | consumed samples: 5839360 | consumed tokens: 11959009280 | elapsed time per iteration (s): 0.25 | learning rate: 8.171E-05 | global batch size: 256 | lm loss: 2.925010E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1024.174 | TFLOPs: 6.52 | +31: iteration 22820/ 37905 | consumed samples: 5841920 | consumed tokens: 11964252160 | elapsed time per iteration (s): 0.19 | learning rate: 8.164E-05 | global batch size: 256 | lm loss: 2.928791E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.629 | TFLOPs: 8.47 | +31: iteration 22830/ 37905 | consumed samples: 5844480 | consumed tokens: 11969495040 | elapsed time per iteration (s): 0.23 | learning rate: 8.157E-05 | global batch size: 256 | lm loss: 2.935366E+00 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.131 | TFLOPs: 7.11 | +31: iteration 22840/ 37905 | consumed samples: 5847040 | consumed tokens: 11974737920 | elapsed time per iteration (s): 0.21 | learning rate: 8.150E-05 | global batch size: 256 | lm loss: 2.908574E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.338 | TFLOPs: 7.72 | +31: iteration 22850/ 37905 | consumed samples: 5849600 | consumed tokens: 11979980800 | elapsed time per iteration (s): 0.24 | learning rate: 8.143E-05 | global batch size: 256 | lm loss: 2.933985E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.971 | TFLOPs: 6.75 | +31: iteration 22860/ 37905 | consumed samples: 5852160 | consumed tokens: 11985223680 | elapsed time per iteration (s): 0.23 | learning rate: 8.136E-05 | global batch size: 256 | lm loss: 2.901393E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.796 | TFLOPs: 7.13 | +31: iteration 22870/ 37905 | consumed samples: 5854720 | consumed tokens: 11990466560 | elapsed time per iteration (s): 0.21 | learning rate: 8.129E-05 | global batch size: 256 | lm loss: 2.938025E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.423 | TFLOPs: 7.88 | +31: iteration 22880/ 37905 | consumed samples: 5857280 | consumed tokens: 11995709440 | elapsed time per iteration (s): 0.23 | learning rate: 8.122E-05 | global batch size: 256 | lm loss: 2.950378E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.865 | TFLOPs: 7.20 | +31: iteration 22890/ 37905 | consumed samples: 5859840 | consumed tokens: 12000952320 | elapsed time per iteration (s): 0.24 | learning rate: 8.115E-05 | global batch size: 256 | lm loss: 2.918533E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.585 | TFLOPs: 6.77 | +31: iteration 22900/ 37905 | consumed samples: 5862400 | consumed tokens: 12006195200 | elapsed time per iteration (s): 0.19 | learning rate: 8.108E-05 | global batch size: 256 | lm loss: 2.951072E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.117 | TFLOPs: 8.39 | +31: iteration 22910/ 37905 | consumed samples: 5864960 | consumed tokens: 12011438080 | elapsed time per iteration (s): 0.22 | learning rate: 8.101E-05 | global batch size: 256 | lm loss: 2.917689E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.700 | TFLOPs: 7.48 | +31: iteration 22920/ 37905 | consumed samples: 5867520 | consumed tokens: 12016680960 | elapsed time per iteration (s): 0.20 | learning rate: 8.094E-05 | global batch size: 256 | lm loss: 2.925475E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.314 | TFLOPs: 8.17 | +31: iteration 22930/ 37905 | consumed samples: 5870080 | consumed tokens: 12021923840 | elapsed time per iteration (s): 0.23 | learning rate: 8.087E-05 | global batch size: 256 | lm loss: 2.922414E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.999 | TFLOPs: 7.09 | +31: iteration 22940/ 37905 | consumed samples: 5872640 | consumed tokens: 12027166720 | elapsed time per iteration (s): 0.23 | learning rate: 8.080E-05 | global batch size: 256 | lm loss: 2.879274E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.543 | TFLOPs: 7.01 | +31: iteration 22950/ 37905 | consumed samples: 5875200 | consumed tokens: 12032409600 | elapsed time per iteration (s): 0.23 | learning rate: 8.072E-05 | global batch size: 256 | lm loss: 2.918567E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.806 | TFLOPs: 7.18 | +31: iteration 22960/ 37905 | consumed samples: 5877760 | consumed tokens: 12037652480 | elapsed time per iteration (s): 0.23 | learning rate: 8.065E-05 | global batch size: 256 | lm loss: 2.936242E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.318 | TFLOPs: 7.07 | +31: iteration 22970/ 37905 | consumed samples: 5880320 | consumed tokens: 12042895360 | elapsed time per iteration (s): 0.50 | learning rate: 8.058E-05 | global batch size: 256 | lm loss: 2.900131E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 515.285 | TFLOPs: 3.28 | +31: iteration 22980/ 37905 | consumed samples: 5882880 | consumed tokens: 12048138240 | elapsed time per iteration (s): 0.27 | learning rate: 8.051E-05 | global batch size: 256 | lm loss: 2.904111E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 932.149 | TFLOPs: 5.94 | +31: iteration 22990/ 37905 | consumed samples: 5885440 | consumed tokens: 12053381120 | elapsed time per iteration (s): 0.19 | learning rate: 8.044E-05 | global batch size: 256 | lm loss: 2.915866E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1372.078 | TFLOPs: 8.74 | +31: iteration 23000/ 37905 | consumed samples: 5888000 | consumed tokens: 12058624000 | elapsed time per iteration (s): 0.23 | learning rate: 8.037E-05 | global batch size: 256 | lm loss: 2.920720E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.702 | TFLOPs: 7.14 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 23000 | lm loss value: 2.825405E+00 | lm loss PPL: 1.686778E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 23000 to checkpoints_83m + 0: [2022-11-24 15:34:26,984] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step23000 is begin to save! + 0: [2022-11-24 15:34:26,993] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,076] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,088] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,110] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,122] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,133] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,144] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,188] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:34:27,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:34:27,189] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step23000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:34:27,189] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:34:27,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:34:27,255] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step23000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:34:27,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 8: [2022-11-24 15:34:27,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,262] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,262] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +11: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,263] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,263] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:34:27,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,264] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,264] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:34:27,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 9: [2022-11-24 15:34:27,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +15: [2022-11-24 15:34:27,265] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 2: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +16: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:34:27,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:34:27,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,266] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +22: [2022-11-24 15:34:27,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 1: [2022-11-24 15:34:27,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,267] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +11: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 8: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:34:27,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:34:27,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,268] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +17: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,268] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +10: [2022-11-24 15:34:27,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,269] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:34:27,269] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:34:27,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,270] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:34:27,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 2: [2022-11-24 15:34:27,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +15: [2022-11-24 15:34:27,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:34:27,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,271] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 9: [2022-11-24 15:34:27,271] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,271] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +24: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +30: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,272] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:34:27,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:34:27,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,273] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +22: [2022-11-24 15:34:27,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +11: [2022-11-24 15:34:27,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,274] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 1: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 8: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +16: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:34:27,275] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,275] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:34:27,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,276] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 9: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 2: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,277] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,277] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +15: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:34:27,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:34:27,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +13: [2022-11-24 15:34:27,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,278] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,278] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:34:27,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +24: [2022-11-24 15:34:27,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:34:27,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:34:27,279] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:34:27,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +30: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +22: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,280] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +11: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 8: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:34:27,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 1: [2022-11-24 15:34:27,281] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:34:27,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +16: [2022-11-24 15:34:27,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:34:27,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,282] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:34:27,282] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +10: [2022-11-24 15:34:27,282] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:34:27,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +14: [2022-11-24 15:34:27,283] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +29: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,283] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +17: [2022-11-24 15:34:27,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,284] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,284] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 2: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:34:27,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +24: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 9: [2022-11-24 15:34:27,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,285] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +15: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +13: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:34:27,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:34:27,286] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 15:34:27,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:34:27,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +30: [2022-11-24 15:34:27,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,287] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:34:27,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +11: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +22: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,288] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 8: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:34:27,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,289] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 15:34:27,289] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +16: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:34:27,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +10: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,290] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:34:27,290] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +17: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,291] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:34:27,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 2: [2022-11-24 15:34:27,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:34:27,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,292] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,292] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 9: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +24: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +15: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +24: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +24: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:34:27,293] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +13: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,293] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:34:27,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +30: [2022-11-24 15:34:27,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,294] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:34:27,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:34:27,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 8: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,295] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +11: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +22: [2022-11-24 15:34:27,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 1: [2022-11-24 15:34:27,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +10: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +16: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:34:27,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:34:27,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +14: [2022-11-24 15:34:27,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +27: [2022-11-24 15:34:27,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:34:27,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +17: [2022-11-24 15:34:27,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:34:27,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:34:27,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 2: [2022-11-24 15:34:27,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 9: [2022-11-24 15:34:27,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:34:27,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +24: [2022-11-24 15:34:27,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +24: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +13: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:34:27,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +30: [2022-11-24 15:34:27,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +11: [2022-11-24 15:34:27,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +22: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 8: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:34:27,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 1: [2022-11-24 15:34:27,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:34:27,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:34:27,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:34:27,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +16: [2022-11-24 15:34:27,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:34:27,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:34:27,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +10: [2022-11-24 15:34:27,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +17: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 2: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 9: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:34:27,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +15: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:34:27,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +24: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:34:27,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +13: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +20: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:34:27,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +30: [2022-11-24 15:34:27,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +21: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +21: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +30: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +11: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +30: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +20: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +26: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +10: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +16: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 6: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +16: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +26: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 4: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +15: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +27: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +15: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +24: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 5: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +25: [2022-11-24 15:34:27,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +22: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 1: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +14: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 3: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +13: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +24: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +12: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +29: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +13: [2022-11-24 15:34:27,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +23: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +18: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +12: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +29: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +13: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +17: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +29: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 7: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +18: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +17: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +27: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +17: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +27: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +19: [2022-11-24 15:34:27,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:34:27,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +31: [2022-11-24 15:34:27,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:34:27,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:34:27,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! +28: [2022-11-24 15:34:27,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:34:27,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step23000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:34:27,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step23000 is ready now! + 0: successfully saved checkpoint at iteration 23000 to checkpoints_83m +31: time (ms) | save-checkpoint: 330.85 +31: iteration 23010/ 37905 | consumed samples: 5890560 | consumed tokens: 12063866880 | elapsed time per iteration (s): 0.24 | learning rate: 8.030E-05 | global batch size: 256 | lm loss: 2.933966E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.168 | TFLOPs: 6.73 | +31: iteration 23020/ 37905 | consumed samples: 5893120 | consumed tokens: 12069109760 | elapsed time per iteration (s): 0.24 | learning rate: 8.023E-05 | global batch size: 256 | lm loss: 2.916522E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.682 | TFLOPs: 6.92 | +31: iteration 23030/ 37905 | consumed samples: 5895680 | consumed tokens: 12074352640 | elapsed time per iteration (s): 0.22 | learning rate: 8.016E-05 | global batch size: 256 | lm loss: 2.914824E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.649 | TFLOPs: 7.46 | +31: iteration 23040/ 37905 | consumed samples: 5898240 | consumed tokens: 12079595520 | elapsed time per iteration (s): 0.21 | learning rate: 8.009E-05 | global batch size: 256 | lm loss: 2.920427E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.391 | TFLOPs: 7.72 | +31: iteration 23050/ 37905 | consumed samples: 5900800 | consumed tokens: 12084838400 | elapsed time per iteration (s): 0.23 | learning rate: 8.002E-05 | global batch size: 256 | lm loss: 2.892949E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1137.219 | TFLOPs: 7.24 | +31: iteration 23060/ 37905 | consumed samples: 5903360 | consumed tokens: 12090081280 | elapsed time per iteration (s): 0.22 | learning rate: 7.995E-05 | global batch size: 256 | lm loss: 2.948388E+00 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.577 | TFLOPs: 7.28 | +31: iteration 23070/ 37905 | consumed samples: 5905920 | consumed tokens: 12095324160 | elapsed time per iteration (s): 0.23 | learning rate: 7.988E-05 | global batch size: 256 | lm loss: 2.915548E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.361 | TFLOPs: 7.01 | +31: iteration 23080/ 37905 | consumed samples: 5908480 | consumed tokens: 12100567040 | elapsed time per iteration (s): 0.22 | learning rate: 7.981E-05 | global batch size: 256 | lm loss: 2.946976E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.717 | TFLOPs: 7.53 | +31: iteration 23090/ 37905 | consumed samples: 5911040 | consumed tokens: 12105809920 | elapsed time per iteration (s): 0.21 | learning rate: 7.974E-05 | global batch size: 256 | lm loss: 2.898370E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.591 | TFLOPs: 7.70 | +31: iteration 23100/ 37905 | consumed samples: 5913600 | consumed tokens: 12111052800 | elapsed time per iteration (s): 0.22 | learning rate: 7.967E-05 | global batch size: 256 | lm loss: 2.913785E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.600 | TFLOPs: 7.54 | +31: iteration 23110/ 37905 | consumed samples: 5916160 | consumed tokens: 12116295680 | elapsed time per iteration (s): 0.24 | learning rate: 7.960E-05 | global batch size: 256 | lm loss: 2.906607E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.429 | TFLOPs: 6.90 | +31: iteration 23120/ 37905 | consumed samples: 5918720 | consumed tokens: 12121538560 | elapsed time per iteration (s): 0.20 | learning rate: 7.953E-05 | global batch size: 256 | lm loss: 2.892841E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.065 | TFLOPs: 7.96 | +31: iteration 23130/ 37905 | consumed samples: 5921280 | consumed tokens: 12126781440 | elapsed time per iteration (s): 0.25 | learning rate: 7.946E-05 | global batch size: 256 | lm loss: 2.971250E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.068 | TFLOPs: 6.56 | +31: iteration 23140/ 37905 | consumed samples: 5923840 | consumed tokens: 12132024320 | elapsed time per iteration (s): 0.21 | learning rate: 7.939E-05 | global batch size: 256 | lm loss: 2.912161E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.328 | TFLOPs: 7.84 | +31: iteration 23150/ 37905 | consumed samples: 5926400 | consumed tokens: 12137267200 | elapsed time per iteration (s): 0.21 | learning rate: 7.932E-05 | global batch size: 256 | lm loss: 2.893304E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.235 | TFLOPs: 7.94 | +31: iteration 23160/ 37905 | consumed samples: 5928960 | consumed tokens: 12142510080 | elapsed time per iteration (s): 0.22 | learning rate: 7.925E-05 | global batch size: 256 | lm loss: 2.882741E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.223 | TFLOPs: 7.53 | +31: iteration 23170/ 37905 | consumed samples: 5931520 | consumed tokens: 12147752960 | elapsed time per iteration (s): 0.18 | learning rate: 7.918E-05 | global batch size: 256 | lm loss: 2.942617E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1388.137 | TFLOPs: 8.84 | +31: iteration 23180/ 37905 | consumed samples: 5934080 | consumed tokens: 12152995840 | elapsed time per iteration (s): 0.24 | learning rate: 7.911E-05 | global batch size: 256 | lm loss: 2.926392E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.096 | TFLOPs: 6.80 | +31: iteration 23190/ 37905 | consumed samples: 5936640 | consumed tokens: 12158238720 | elapsed time per iteration (s): 0.23 | learning rate: 7.904E-05 | global batch size: 256 | lm loss: 2.945135E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.070 | TFLOPs: 7.08 | +31: iteration 23200/ 37905 | consumed samples: 5939200 | consumed tokens: 12163481600 | elapsed time per iteration (s): 0.22 | learning rate: 7.897E-05 | global batch size: 256 | lm loss: 2.928020E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.280 | TFLOPs: 7.50 | +31: iteration 23210/ 37905 | consumed samples: 5941760 | consumed tokens: 12168724480 | elapsed time per iteration (s): 0.26 | learning rate: 7.890E-05 | global batch size: 256 | lm loss: 2.903860E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.104 | TFLOPs: 6.34 | +31: iteration 23220/ 37905 | consumed samples: 5944320 | consumed tokens: 12173967360 | elapsed time per iteration (s): 0.19 | learning rate: 7.883E-05 | global batch size: 256 | lm loss: 2.922988E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.541 | TFLOPs: 8.57 | +31: iteration 23230/ 37905 | consumed samples: 5946880 | consumed tokens: 12179210240 | elapsed time per iteration (s): 0.21 | learning rate: 7.876E-05 | global batch size: 256 | lm loss: 2.912200E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.502 | TFLOPs: 7.66 | +31: iteration 23240/ 37905 | consumed samples: 5949440 | consumed tokens: 12184453120 | elapsed time per iteration (s): 0.25 | learning rate: 7.869E-05 | global batch size: 256 | lm loss: 2.918755E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1024.299 | TFLOPs: 6.52 | +31: iteration 23250/ 37905 | consumed samples: 5952000 | consumed tokens: 12189696000 | elapsed time per iteration (s): 0.24 | learning rate: 7.862E-05 | global batch size: 256 | lm loss: 2.950993E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.843 | TFLOPs: 6.79 | +31: iteration 23260/ 37905 | consumed samples: 5954560 | consumed tokens: 12194938880 | elapsed time per iteration (s): 0.21 | learning rate: 7.855E-05 | global batch size: 256 | lm loss: 2.906693E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.608 | TFLOPs: 7.67 | +31: iteration 23270/ 37905 | consumed samples: 5957120 | consumed tokens: 12200181760 | elapsed time per iteration (s): 0.22 | learning rate: 7.848E-05 | global batch size: 256 | lm loss: 2.938885E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.028 | TFLOPs: 7.50 | +31: iteration 23280/ 37905 | consumed samples: 5959680 | consumed tokens: 12205424640 | elapsed time per iteration (s): 0.21 | learning rate: 7.841E-05 | global batch size: 256 | lm loss: 2.920266E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.453 | TFLOPs: 7.84 | +31: iteration 23290/ 37905 | consumed samples: 5962240 | consumed tokens: 12210667520 | elapsed time per iteration (s): 0.22 | learning rate: 7.834E-05 | global batch size: 256 | lm loss: 2.912829E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.763 | TFLOPs: 7.38 | +31: iteration 23300/ 37905 | consumed samples: 5964800 | consumed tokens: 12215910400 | elapsed time per iteration (s): 0.25 | learning rate: 7.827E-05 | global batch size: 256 | lm loss: 2.945416E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.849 | TFLOPs: 6.65 | +31: iteration 23310/ 37905 | consumed samples: 5967360 | consumed tokens: 12221153280 | elapsed time per iteration (s): 0.21 | learning rate: 7.820E-05 | global batch size: 256 | lm loss: 2.923172E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.229 | TFLOPs: 7.66 | +31: iteration 23320/ 37905 | consumed samples: 5969920 | consumed tokens: 12226396160 | elapsed time per iteration (s): 0.21 | learning rate: 7.813E-05 | global batch size: 256 | lm loss: 2.938423E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.557 | TFLOPs: 7.89 | +31: iteration 23330/ 37905 | consumed samples: 5972480 | consumed tokens: 12231639040 | elapsed time per iteration (s): 0.19 | learning rate: 7.806E-05 | global batch size: 256 | lm loss: 2.909385E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.005 | TFLOPs: 8.43 | +31: iteration 23340/ 37905 | consumed samples: 5975040 | consumed tokens: 12236881920 | elapsed time per iteration (s): 0.23 | learning rate: 7.799E-05 | global batch size: 256 | lm loss: 2.937871E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.154 | TFLOPs: 7.11 | +31: iteration 23350/ 37905 | consumed samples: 5977600 | consumed tokens: 12242124800 | elapsed time per iteration (s): 0.22 | learning rate: 7.792E-05 | global batch size: 256 | lm loss: 2.931329E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.403 | TFLOPs: 7.38 | +31: iteration 23360/ 37905 | consumed samples: 5980160 | consumed tokens: 12247367680 | elapsed time per iteration (s): 0.19 | learning rate: 7.785E-05 | global batch size: 256 | lm loss: 2.935300E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1350.458 | TFLOPs: 8.60 | +31: iteration 23370/ 37905 | consumed samples: 5982720 | consumed tokens: 12252610560 | elapsed time per iteration (s): 0.25 | learning rate: 7.778E-05 | global batch size: 256 | lm loss: 2.915947E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.047 | TFLOPs: 6.51 | +31: iteration 23380/ 37905 | consumed samples: 5985280 | consumed tokens: 12257853440 | elapsed time per iteration (s): 0.24 | learning rate: 7.771E-05 | global batch size: 256 | lm loss: 2.940618E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.157 | TFLOPs: 6.85 | +31: iteration 23390/ 37905 | consumed samples: 5987840 | consumed tokens: 12263096320 | elapsed time per iteration (s): 0.22 | learning rate: 7.764E-05 | global batch size: 256 | lm loss: 2.916545E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.719 | TFLOPs: 7.58 | +31: iteration 23400/ 37905 | consumed samples: 5990400 | consumed tokens: 12268339200 | elapsed time per iteration (s): 0.21 | learning rate: 7.757E-05 | global batch size: 256 | lm loss: 2.886394E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.952 | TFLOPs: 7.88 | +31: iteration 23410/ 37905 | consumed samples: 5992960 | consumed tokens: 12273582080 | elapsed time per iteration (s): 0.20 | learning rate: 7.750E-05 | global batch size: 256 | lm loss: 2.916960E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.199 | TFLOPs: 7.99 | +31: iteration 23420/ 37905 | consumed samples: 5995520 | consumed tokens: 12278824960 | elapsed time per iteration (s): 0.21 | learning rate: 7.743E-05 | global batch size: 256 | lm loss: 2.929622E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.813 | TFLOPs: 7.81 | +31: iteration 23430/ 37905 | consumed samples: 5998080 | consumed tokens: 12284067840 | elapsed time per iteration (s): 0.22 | learning rate: 7.736E-05 | global batch size: 256 | lm loss: 2.908002E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.795 | TFLOPs: 7.34 | +31: iteration 23440/ 37905 | consumed samples: 6000640 | consumed tokens: 12289310720 | elapsed time per iteration (s): 0.26 | learning rate: 7.729E-05 | global batch size: 256 | lm loss: 2.932709E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 997.593 | TFLOPs: 6.35 | +31: iteration 23450/ 37905 | consumed samples: 6003200 | consumed tokens: 12294553600 | elapsed time per iteration (s): 0.21 | learning rate: 7.722E-05 | global batch size: 256 | lm loss: 2.905626E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.711 | TFLOPs: 7.70 | +31: iteration 23460/ 37905 | consumed samples: 6005760 | consumed tokens: 12299796480 | elapsed time per iteration (s): 0.21 | learning rate: 7.715E-05 | global batch size: 256 | lm loss: 2.905769E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1208.248 | TFLOPs: 7.70 | +31: iteration 23470/ 37905 | consumed samples: 6008320 | consumed tokens: 12305039360 | elapsed time per iteration (s): 0.22 | learning rate: 7.708E-05 | global batch size: 256 | lm loss: 2.943047E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.711 | TFLOPs: 7.25 | +31: iteration 23480/ 37905 | consumed samples: 6010880 | consumed tokens: 12310282240 | elapsed time per iteration (s): 0.25 | learning rate: 7.702E-05 | global batch size: 256 | lm loss: 2.940140E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.372 | TFLOPs: 6.58 | +31: iteration 23490/ 37905 | consumed samples: 6013440 | consumed tokens: 12315525120 | elapsed time per iteration (s): 0.25 | learning rate: 7.695E-05 | global batch size: 256 | lm loss: 2.932985E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.385 | TFLOPs: 6.43 | +31: iteration 23500/ 37905 | consumed samples: 6016000 | consumed tokens: 12320768000 | elapsed time per iteration (s): 0.25 | learning rate: 7.688E-05 | global batch size: 256 | lm loss: 2.934714E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.215 | TFLOPs: 6.51 | +31: iteration 23510/ 37905 | consumed samples: 6018560 | consumed tokens: 12326010880 | elapsed time per iteration (s): 0.22 | learning rate: 7.681E-05 | global batch size: 256 | lm loss: 2.890210E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.599 | TFLOPs: 7.40 | +31: iteration 23520/ 37905 | consumed samples: 6021120 | consumed tokens: 12331253760 | elapsed time per iteration (s): 0.22 | learning rate: 7.674E-05 | global batch size: 256 | lm loss: 2.947550E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.515 | TFLOPs: 7.49 | +31: iteration 23530/ 37905 | consumed samples: 6023680 | consumed tokens: 12336496640 | elapsed time per iteration (s): 0.22 | learning rate: 7.667E-05 | global batch size: 256 | lm loss: 2.931663E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.702 | TFLOPs: 7.48 | +31: iteration 23540/ 37905 | consumed samples: 6026240 | consumed tokens: 12341739520 | elapsed time per iteration (s): 0.24 | learning rate: 7.660E-05 | global batch size: 256 | lm loss: 3.022237E+00 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.711 | TFLOPs: 6.79 | +31: iteration 23550/ 37905 | consumed samples: 6028800 | consumed tokens: 12346982400 | elapsed time per iteration (s): 0.25 | learning rate: 7.653E-05 | global batch size: 256 | lm loss: 2.968093E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.246 | TFLOPs: 6.61 | +31: iteration 23560/ 37905 | consumed samples: 6031360 | consumed tokens: 12352225280 | elapsed time per iteration (s): 0.22 | learning rate: 7.646E-05 | global batch size: 256 | lm loss: 2.951448E+00 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.245 | TFLOPs: 7.33 | +31: iteration 23570/ 37905 | consumed samples: 6033920 | consumed tokens: 12357468160 | elapsed time per iteration (s): 0.21 | learning rate: 7.639E-05 | global batch size: 256 | lm loss: 2.921167E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.439 | TFLOPs: 7.87 | +31: iteration 23580/ 37905 | consumed samples: 6036480 | consumed tokens: 12362711040 | elapsed time per iteration (s): 0.22 | learning rate: 7.632E-05 | global batch size: 256 | lm loss: 2.912118E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.424 | TFLOPs: 7.35 | +31: iteration 23590/ 37905 | consumed samples: 6039040 | consumed tokens: 12367953920 | elapsed time per iteration (s): 0.23 | learning rate: 7.625E-05 | global batch size: 256 | lm loss: 2.889475E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.966 | TFLOPs: 7.20 | +31: iteration 23600/ 37905 | consumed samples: 6041600 | consumed tokens: 12373196800 | elapsed time per iteration (s): 0.19 | learning rate: 7.618E-05 | global batch size: 256 | lm loss: 2.920904E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.341 | TFLOPs: 8.63 | +31: iteration 23610/ 37905 | consumed samples: 6044160 | consumed tokens: 12378439680 | elapsed time per iteration (s): 0.24 | learning rate: 7.612E-05 | global batch size: 256 | lm loss: 2.936838E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.952 | TFLOPs: 6.89 | +31: iteration 23620/ 37905 | consumed samples: 6046720 | consumed tokens: 12383682560 | elapsed time per iteration (s): 0.23 | learning rate: 7.605E-05 | global batch size: 256 | lm loss: 2.955991E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.449 | TFLOPs: 7.06 | +31: iteration 23630/ 37905 | consumed samples: 6049280 | consumed tokens: 12388925440 | elapsed time per iteration (s): 0.23 | learning rate: 7.598E-05 | global batch size: 256 | lm loss: 2.904957E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.039 | TFLOPs: 7.01 | +31: iteration 23640/ 37905 | consumed samples: 6051840 | consumed tokens: 12394168320 | elapsed time per iteration (s): 0.24 | learning rate: 7.591E-05 | global batch size: 256 | lm loss: 2.918507E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.397 | TFLOPs: 6.86 | +31: iteration 23650/ 37905 | consumed samples: 6054400 | consumed tokens: 12399411200 | elapsed time per iteration (s): 0.20 | learning rate: 7.584E-05 | global batch size: 256 | lm loss: 2.878356E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.966 | TFLOPs: 8.10 | +31: iteration 23660/ 37905 | consumed samples: 6056960 | consumed tokens: 12404654080 | elapsed time per iteration (s): 0.21 | learning rate: 7.577E-05 | global batch size: 256 | lm loss: 2.927824E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.386 | TFLOPs: 7.89 | +31: iteration 23670/ 37905 | consumed samples: 6059520 | consumed tokens: 12409896960 | elapsed time per iteration (s): 0.22 | learning rate: 7.570E-05 | global batch size: 256 | lm loss: 2.918754E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.179 | TFLOPs: 7.30 | +31: iteration 23680/ 37905 | consumed samples: 6062080 | consumed tokens: 12415139840 | elapsed time per iteration (s): 0.24 | learning rate: 7.563E-05 | global batch size: 256 | lm loss: 2.913893E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.780 | TFLOPs: 6.90 | +31: iteration 23690/ 37905 | consumed samples: 6064640 | consumed tokens: 12420382720 | elapsed time per iteration (s): 0.21 | learning rate: 7.556E-05 | global batch size: 256 | lm loss: 2.927267E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.081 | TFLOPs: 7.88 | +31: iteration 23700/ 37905 | consumed samples: 6067200 | consumed tokens: 12425625600 | elapsed time per iteration (s): 0.19 | learning rate: 7.549E-05 | global batch size: 256 | lm loss: 2.930224E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.286 | TFLOPs: 8.39 | +31: iteration 23710/ 37905 | consumed samples: 6069760 | consumed tokens: 12430868480 | elapsed time per iteration (s): 0.24 | learning rate: 7.543E-05 | global batch size: 256 | lm loss: 2.919978E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.361 | TFLOPs: 6.71 | +31: iteration 23720/ 37905 | consumed samples: 6072320 | consumed tokens: 12436111360 | elapsed time per iteration (s): 0.23 | learning rate: 7.536E-05 | global batch size: 256 | lm loss: 2.913877E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.750 | TFLOPs: 7.04 | +31: iteration 23730/ 37905 | consumed samples: 6074880 | consumed tokens: 12441354240 | elapsed time per iteration (s): 0.22 | learning rate: 7.529E-05 | global batch size: 256 | lm loss: 2.943867E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.175 | TFLOPs: 7.41 | +31: iteration 23740/ 37905 | consumed samples: 6077440 | consumed tokens: 12446597120 | elapsed time per iteration (s): 0.20 | learning rate: 7.522E-05 | global batch size: 256 | lm loss: 2.882794E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.066 | TFLOPs: 8.00 | +31: iteration 23750/ 37905 | consumed samples: 6080000 | consumed tokens: 12451840000 | elapsed time per iteration (s): 0.22 | learning rate: 7.515E-05 | global batch size: 256 | lm loss: 2.888490E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.772 | TFLOPs: 7.56 | +31: iteration 23760/ 37905 | consumed samples: 6082560 | consumed tokens: 12457082880 | elapsed time per iteration (s): 0.23 | learning rate: 7.508E-05 | global batch size: 256 | lm loss: 2.905875E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.506 | TFLOPs: 7.23 | +31: iteration 23770/ 37905 | consumed samples: 6085120 | consumed tokens: 12462325760 | elapsed time per iteration (s): 0.22 | learning rate: 7.501E-05 | global batch size: 256 | lm loss: 2.933536E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.457 | TFLOPs: 7.28 | +31: iteration 23780/ 37905 | consumed samples: 6087680 | consumed tokens: 12467568640 | elapsed time per iteration (s): 0.21 | learning rate: 7.494E-05 | global batch size: 256 | lm loss: 2.944143E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.760 | TFLOPs: 7.67 | +31: iteration 23790/ 37905 | consumed samples: 6090240 | consumed tokens: 12472811520 | elapsed time per iteration (s): 0.19 | learning rate: 7.488E-05 | global batch size: 256 | lm loss: 2.948140E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.131 | TFLOPs: 8.41 | +31: iteration 23800/ 37905 | consumed samples: 6092800 | consumed tokens: 12478054400 | elapsed time per iteration (s): 0.23 | learning rate: 7.481E-05 | global batch size: 256 | lm loss: 2.921918E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.329 | TFLOPs: 7.14 | +31: iteration 23810/ 37905 | consumed samples: 6095360 | consumed tokens: 12483297280 | elapsed time per iteration (s): 0.20 | learning rate: 7.474E-05 | global batch size: 256 | lm loss: 2.901225E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1285.020 | TFLOPs: 8.18 | +31: iteration 23820/ 37905 | consumed samples: 6097920 | consumed tokens: 12488540160 | elapsed time per iteration (s): 0.21 | learning rate: 7.467E-05 | global batch size: 256 | lm loss: 2.907585E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.327 | TFLOPs: 7.75 | +31: iteration 23830/ 37905 | consumed samples: 6100480 | consumed tokens: 12493783040 | elapsed time per iteration (s): 0.22 | learning rate: 7.460E-05 | global batch size: 256 | lm loss: 2.921783E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.705 | TFLOPs: 7.33 | +31: iteration 23840/ 37905 | consumed samples: 6103040 | consumed tokens: 12499025920 | elapsed time per iteration (s): 0.23 | learning rate: 7.453E-05 | global batch size: 256 | lm loss: 2.882632E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.051 | TFLOPs: 6.97 | +31: iteration 23850/ 37905 | consumed samples: 6105600 | consumed tokens: 12504268800 | elapsed time per iteration (s): 0.20 | learning rate: 7.446E-05 | global batch size: 256 | lm loss: 2.924886E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1304.288 | TFLOPs: 8.31 | +31: iteration 23860/ 37905 | consumed samples: 6108160 | consumed tokens: 12509511680 | elapsed time per iteration (s): 0.21 | learning rate: 7.440E-05 | global batch size: 256 | lm loss: 2.889565E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.753 | TFLOPs: 7.73 | +31: iteration 23870/ 37905 | consumed samples: 6110720 | consumed tokens: 12514754560 | elapsed time per iteration (s): 0.21 | learning rate: 7.433E-05 | global batch size: 256 | lm loss: 2.920973E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.895 | TFLOPs: 7.69 | +31: iteration 23880/ 37905 | consumed samples: 6113280 | consumed tokens: 12519997440 | elapsed time per iteration (s): 0.22 | learning rate: 7.426E-05 | global batch size: 256 | lm loss: 2.949175E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.997 | TFLOPs: 7.25 | +31: iteration 23890/ 37905 | consumed samples: 6115840 | consumed tokens: 12525240320 | elapsed time per iteration (s): 0.22 | learning rate: 7.419E-05 | global batch size: 256 | lm loss: 2.920948E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.201 | TFLOPs: 7.34 | +31: iteration 23900/ 37905 | consumed samples: 6118400 | consumed tokens: 12530483200 | elapsed time per iteration (s): 0.23 | learning rate: 7.412E-05 | global batch size: 256 | lm loss: 2.962405E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1136.660 | TFLOPs: 7.24 | +31: iteration 23910/ 37905 | consumed samples: 6120960 | consumed tokens: 12535726080 | elapsed time per iteration (s): 0.25 | learning rate: 7.405E-05 | global batch size: 256 | lm loss: 2.913646E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1026.646 | TFLOPs: 6.54 | +31: iteration 23920/ 37905 | consumed samples: 6123520 | consumed tokens: 12540968960 | elapsed time per iteration (s): 0.20 | learning rate: 7.398E-05 | global batch size: 256 | lm loss: 2.899866E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.920 | TFLOPs: 8.16 | +31: iteration 23930/ 37905 | consumed samples: 6126080 | consumed tokens: 12546211840 | elapsed time per iteration (s): 0.19 | learning rate: 7.392E-05 | global batch size: 256 | lm loss: 2.939954E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.753 | TFLOPs: 8.44 | +31: iteration 23940/ 37905 | consumed samples: 6128640 | consumed tokens: 12551454720 | elapsed time per iteration (s): 0.22 | learning rate: 7.385E-05 | global batch size: 256 | lm loss: 2.912992E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.867 | TFLOPs: 7.56 | +31: iteration 23950/ 37905 | consumed samples: 6131200 | consumed tokens: 12556697600 | elapsed time per iteration (s): 0.23 | learning rate: 7.378E-05 | global batch size: 256 | lm loss: 2.915618E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.111 | TFLOPs: 7.20 | +31: iteration 23960/ 37905 | consumed samples: 6133760 | consumed tokens: 12561940480 | elapsed time per iteration (s): 0.21 | learning rate: 7.371E-05 | global batch size: 256 | lm loss: 2.890935E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.408 | TFLOPs: 7.64 | +31: iteration 23970/ 37905 | consumed samples: 6136320 | consumed tokens: 12567183360 | elapsed time per iteration (s): 0.23 | learning rate: 7.364E-05 | global batch size: 256 | lm loss: 2.927011E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.038 | TFLOPs: 7.18 | +31: iteration 23980/ 37905 | consumed samples: 6138880 | consumed tokens: 12572426240 | elapsed time per iteration (s): 0.21 | learning rate: 7.357E-05 | global batch size: 256 | lm loss: 2.931717E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.336 | TFLOPs: 7.72 | +31: iteration 23990/ 37905 | consumed samples: 6141440 | consumed tokens: 12577669120 | elapsed time per iteration (s): 0.21 | learning rate: 7.351E-05 | global batch size: 256 | lm loss: 2.935959E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.175 | TFLOPs: 7.78 | + 0: [2022-11-24 15:38:07,373] [INFO] [logging.py:68:log_dist] [Rank 0] step=24000, skipped=0, lr=[7.343835488865024e-05, 7.343835488865024e-05, 7.343835488865024e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 24000/ 37905 | consumed samples: 6144000 | consumed tokens: 12582912000 | elapsed time per iteration (s): 0.20 | learning rate: 7.344E-05 | global batch size: 256 | lm loss: 2.909592E+00 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1312.074 | TFLOPs: 8.36 | + 0: steps: 24000 loss: 3.0016 iter time (s): 0.222 samples/sec: 1155.554 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 24000 | lm loss value: 2.825516E+00 | lm loss PPL: 1.686964E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 24000 to checkpoints_83m + 0: [2022-11-24 15:38:07,457] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step24000 is begin to save! + 0: [2022-11-24 15:38:07,466] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,585] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,597] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,609] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,632] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,644] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:38:07,668] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:38:07,669] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step24000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:38:07,669] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:38:07,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:38:07,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step24000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:38:07,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:38:07,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:38:07,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +12: [2022-11-24 15:38:07,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:38:07,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +30: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:38:07,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +31: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:38:07,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +21: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +16: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +24: [2022-11-24 15:38:07,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +18: [2022-11-24 15:38:07,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:38:07,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +22: [2022-11-24 15:38:07,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +22: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:38:07,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 8: [2022-11-24 15:38:07,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:38:07,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 4: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:38:07,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +30: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 2: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:38:07,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:38:07,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +26: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:38:07,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:38:07,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:38:07,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +31: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +11: [2022-11-24 15:38:07,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +16: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +21: [2022-11-24 15:38:07,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +24: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +24: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +18: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +18: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +22: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +22: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:38:07,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:38:07,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:38:07,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 4: [2022-11-24 15:38:07,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +30: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:38:07,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:38:07,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +15: [2022-11-24 15:38:07,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:38:07,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +12: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:38:07,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 2: [2022-11-24 15:38:07,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +31: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:38:07,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +11: [2022-11-24 15:38:07,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +21: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +24: [2022-11-24 15:38:07,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:38:07,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +14: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +18: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 8: [2022-11-24 15:38:07,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:38:07,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +22: [2022-11-24 15:38:07,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:38:07,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:38:07,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:38:07,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:38:07,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 4: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +30: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +15: [2022-11-24 15:38:07,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +12: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 2: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:38:07,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +31: [2022-11-24 15:38:07,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +31: [2022-11-24 15:38:07,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:38:07,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +21: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +14: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +24: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:38:07,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:38:07,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +18: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 8: [2022-11-24 15:38:07,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:38:07,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:38:07,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +22: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:38:07,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:38:07,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 4: [2022-11-24 15:38:07,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +30: [2022-11-24 15:38:07,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:38:07,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:38:07,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +15: [2022-11-24 15:38:07,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:38:07,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +12: [2022-11-24 15:38:07,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:38:07,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:38:07,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 2: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:38:07,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +31: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +11: [2022-11-24 15:38:07,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +31: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:38:07,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:38:07,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +21: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +14: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +24: [2022-11-24 15:38:07,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:38:07,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:38:07,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +18: [2022-11-24 15:38:07,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:38:07,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:38:07,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 8: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +22: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 15:38:07,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:38:07,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:38:07,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:38:07,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 4: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +30: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +15: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:38:07,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:38:07,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +12: [2022-11-24 15:38:07,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:38:07,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:38:07,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +31: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 15:38:07,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 2: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:38:07,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +14: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +21: [2022-11-24 15:38:07,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +24: [2022-11-24 15:38:07,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:38:07,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +18: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:38:07,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:38:07,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 8: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:38:07,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +22: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:38:07,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:38:07,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:38:07,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +30: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 4: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +26: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:38:07,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +15: [2022-11-24 15:38:07,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:38:07,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:38:07,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +12: [2022-11-24 15:38:07,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:38:07,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +17: [2022-11-24 15:38:07,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +31: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:38:07,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:38:07,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:38:07,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +18: [2022-11-24 15:38:07,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +21: [2022-11-24 15:38:07,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:38:07,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +16: [2022-11-24 15:38:07,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +14: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 5: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +27: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +13: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +26: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +22: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 8: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +13: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +24: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +22: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +14: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +20: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +18: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +20: [2022-11-24 15:38:07,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +23: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:38:07,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +15: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +11: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +30: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +15: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 7: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +17: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 9: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +12: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +16: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 1: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +14: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 8: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +23: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +11: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +12: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +31: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 6: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +21: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +28: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +19: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +22: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +26: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +28: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +19: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +22: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +29: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +31: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 3: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 4: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +25: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +29: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +25: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 2: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +10: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 2: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step24000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! +10: [2022-11-24 15:38:07,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step24000 is ready now! + 0: successfully saved checkpoint at iteration 24000 to checkpoints_83m +31: time (ms) | save-checkpoint: 338.53 +31: iteration 24010/ 37905 | consumed samples: 6146560 | consumed tokens: 12588154880 | elapsed time per iteration (s): 0.23 | learning rate: 7.337E-05 | global batch size: 256 | lm loss: 2.898805E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.119 | TFLOPs: 6.99 | +31: iteration 24020/ 37905 | consumed samples: 6149120 | consumed tokens: 12593397760 | elapsed time per iteration (s): 0.20 | learning rate: 7.330E-05 | global batch size: 256 | lm loss: 2.913963E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.135 | TFLOPs: 8.11 | +31: iteration 24030/ 37905 | consumed samples: 6151680 | consumed tokens: 12598640640 | elapsed time per iteration (s): 0.19 | learning rate: 7.323E-05 | global batch size: 256 | lm loss: 2.943394E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.505 | TFLOPs: 8.40 | +31: iteration 24040/ 37905 | consumed samples: 6154240 | consumed tokens: 12603883520 | elapsed time per iteration (s): 0.22 | learning rate: 7.317E-05 | global batch size: 256 | lm loss: 2.908361E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.313 | TFLOPs: 7.46 | +31: iteration 24050/ 37905 | consumed samples: 6156800 | consumed tokens: 12609126400 | elapsed time per iteration (s): 0.21 | learning rate: 7.310E-05 | global batch size: 256 | lm loss: 2.930038E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.317 | TFLOPs: 7.66 | +31: iteration 24060/ 37905 | consumed samples: 6159360 | consumed tokens: 12614369280 | elapsed time per iteration (s): 0.25 | learning rate: 7.303E-05 | global batch size: 256 | lm loss: 2.928140E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.360 | TFLOPs: 6.59 | +31: iteration 24070/ 37905 | consumed samples: 6161920 | consumed tokens: 12619612160 | elapsed time per iteration (s): 0.23 | learning rate: 7.296E-05 | global batch size: 256 | lm loss: 2.911843E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.853 | TFLOPs: 7.20 | +31: iteration 24080/ 37905 | consumed samples: 6164480 | consumed tokens: 12624855040 | elapsed time per iteration (s): 0.19 | learning rate: 7.289E-05 | global batch size: 256 | lm loss: 2.939254E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.642 | TFLOPs: 8.37 | +31: iteration 24090/ 37905 | consumed samples: 6167040 | consumed tokens: 12630097920 | elapsed time per iteration (s): 0.20 | learning rate: 7.283E-05 | global batch size: 256 | lm loss: 2.913720E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.493 | TFLOPs: 7.98 | +31: iteration 24100/ 37905 | consumed samples: 6169600 | consumed tokens: 12635340800 | elapsed time per iteration (s): 0.22 | learning rate: 7.276E-05 | global batch size: 256 | lm loss: 2.890710E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.125 | TFLOPs: 7.30 | +31: iteration 24110/ 37905 | consumed samples: 6172160 | consumed tokens: 12640583680 | elapsed time per iteration (s): 0.24 | learning rate: 7.269E-05 | global batch size: 256 | lm loss: 2.927798E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.237 | TFLOPs: 6.74 | +31: iteration 24120/ 37905 | consumed samples: 6174720 | consumed tokens: 12645826560 | elapsed time per iteration (s): 0.23 | learning rate: 7.262E-05 | global batch size: 256 | lm loss: 2.921029E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.119 | TFLOPs: 7.17 | +31: iteration 24130/ 37905 | consumed samples: 6177280 | consumed tokens: 12651069440 | elapsed time per iteration (s): 0.26 | learning rate: 7.255E-05 | global batch size: 256 | lm loss: 2.925887E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 994.580 | TFLOPs: 6.33 | +31: iteration 24140/ 37905 | consumed samples: 6179840 | consumed tokens: 12656312320 | elapsed time per iteration (s): 0.23 | learning rate: 7.249E-05 | global batch size: 256 | lm loss: 2.883369E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.788 | TFLOPs: 7.09 | +31: iteration 24150/ 37905 | consumed samples: 6182400 | consumed tokens: 12661555200 | elapsed time per iteration (s): 0.22 | learning rate: 7.242E-05 | global batch size: 256 | lm loss: 2.926097E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.417 | TFLOPs: 7.45 | +31: iteration 24160/ 37905 | consumed samples: 6184960 | consumed tokens: 12666798080 | elapsed time per iteration (s): 0.27 | learning rate: 7.235E-05 | global batch size: 256 | lm loss: 2.929445E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 952.108 | TFLOPs: 6.06 | +31: iteration 24170/ 37905 | consumed samples: 6187520 | consumed tokens: 12672040960 | elapsed time per iteration (s): 0.20 | learning rate: 7.228E-05 | global batch size: 256 | lm loss: 2.911651E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.826 | TFLOPs: 8.06 | +31: iteration 24180/ 37905 | consumed samples: 6190080 | consumed tokens: 12677283840 | elapsed time per iteration (s): 0.20 | learning rate: 7.222E-05 | global batch size: 256 | lm loss: 2.927777E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.634 | TFLOPs: 8.09 | +31: iteration 24190/ 37905 | consumed samples: 6192640 | consumed tokens: 12682526720 | elapsed time per iteration (s): 0.23 | learning rate: 7.215E-05 | global batch size: 256 | lm loss: 2.910669E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.518 | TFLOPs: 7.06 | +31: iteration 24200/ 37905 | consumed samples: 6195200 | consumed tokens: 12687769600 | elapsed time per iteration (s): 0.21 | learning rate: 7.208E-05 | global batch size: 256 | lm loss: 2.940459E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.210 | TFLOPs: 7.60 | +31: iteration 24210/ 37905 | consumed samples: 6197760 | consumed tokens: 12693012480 | elapsed time per iteration (s): 0.21 | learning rate: 7.201E-05 | global batch size: 256 | lm loss: 2.918488E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.632 | TFLOPs: 7.73 | +31: iteration 24220/ 37905 | consumed samples: 6200320 | consumed tokens: 12698255360 | elapsed time per iteration (s): 0.20 | learning rate: 7.194E-05 | global batch size: 256 | lm loss: 2.889588E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.882 | TFLOPs: 8.21 | +31: iteration 24230/ 37905 | consumed samples: 6202880 | consumed tokens: 12703498240 | elapsed time per iteration (s): 0.21 | learning rate: 7.188E-05 | global batch size: 256 | lm loss: 2.906100E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.307 | TFLOPs: 7.78 | +31: iteration 24240/ 37905 | consumed samples: 6205440 | consumed tokens: 12708741120 | elapsed time per iteration (s): 0.22 | learning rate: 7.181E-05 | global batch size: 256 | lm loss: 2.918207E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1188.462 | TFLOPs: 7.57 | +31: iteration 24250/ 37905 | consumed samples: 6208000 | consumed tokens: 12713984000 | elapsed time per iteration (s): 0.22 | learning rate: 7.174E-05 | global batch size: 256 | lm loss: 2.922625E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.801 | TFLOPs: 7.55 | +31: iteration 24260/ 37905 | consumed samples: 6210560 | consumed tokens: 12719226880 | elapsed time per iteration (s): 0.21 | learning rate: 7.167E-05 | global batch size: 256 | lm loss: 2.915328E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.995 | TFLOPs: 7.62 | +31: iteration 24270/ 37905 | consumed samples: 6213120 | consumed tokens: 12724469760 | elapsed time per iteration (s): 0.25 | learning rate: 7.161E-05 | global batch size: 256 | lm loss: 2.937948E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1007.046 | TFLOPs: 6.41 | +31: iteration 24280/ 37905 | consumed samples: 6215680 | consumed tokens: 12729712640 | elapsed time per iteration (s): 0.26 | learning rate: 7.154E-05 | global batch size: 256 | lm loss: 2.921922E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 999.291 | TFLOPs: 6.36 | +31: iteration 24290/ 37905 | consumed samples: 6218240 | consumed tokens: 12734955520 | elapsed time per iteration (s): 0.23 | learning rate: 7.147E-05 | global batch size: 256 | lm loss: 2.889569E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.659 | TFLOPs: 7.05 | +31: iteration 24300/ 37905 | consumed samples: 6220800 | consumed tokens: 12740198400 | elapsed time per iteration (s): 0.24 | learning rate: 7.141E-05 | global batch size: 256 | lm loss: 2.907747E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.658 | TFLOPs: 6.82 | +31: iteration 24310/ 37905 | consumed samples: 6223360 | consumed tokens: 12745441280 | elapsed time per iteration (s): 0.22 | learning rate: 7.134E-05 | global batch size: 256 | lm loss: 2.906697E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.171 | TFLOPs: 7.38 | +31: iteration 24320/ 37905 | consumed samples: 6225920 | consumed tokens: 12750684160 | elapsed time per iteration (s): 0.24 | learning rate: 7.127E-05 | global batch size: 256 | lm loss: 2.918153E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.031 | TFLOPs: 6.70 | +31: iteration 24330/ 37905 | consumed samples: 6228480 | consumed tokens: 12755927040 | elapsed time per iteration (s): 0.19 | learning rate: 7.120E-05 | global batch size: 256 | lm loss: 2.916596E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.587 | TFLOPs: 8.37 | +31: iteration 24340/ 37905 | consumed samples: 6231040 | consumed tokens: 12761169920 | elapsed time per iteration (s): 0.20 | learning rate: 7.114E-05 | global batch size: 256 | lm loss: 2.928420E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1300.635 | TFLOPs: 8.28 | +31: iteration 24350/ 37905 | consumed samples: 6233600 | consumed tokens: 12766412800 | elapsed time per iteration (s): 0.21 | learning rate: 7.107E-05 | global batch size: 256 | lm loss: 2.921620E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.905 | TFLOPs: 7.58 | +31: iteration 24360/ 37905 | consumed samples: 6236160 | consumed tokens: 12771655680 | elapsed time per iteration (s): 0.25 | learning rate: 7.100E-05 | global batch size: 256 | lm loss: 2.916123E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.401 | TFLOPs: 6.62 | +31: iteration 24370/ 37905 | consumed samples: 6238720 | consumed tokens: 12776898560 | elapsed time per iteration (s): 0.21 | learning rate: 7.093E-05 | global batch size: 256 | lm loss: 2.928957E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.245 | TFLOPs: 7.82 | +31: iteration 24380/ 37905 | consumed samples: 6241280 | consumed tokens: 12782141440 | elapsed time per iteration (s): 0.20 | learning rate: 7.087E-05 | global batch size: 256 | lm loss: 2.882782E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.274 | TFLOPs: 7.98 | +31: iteration 24390/ 37905 | consumed samples: 6243840 | consumed tokens: 12787384320 | elapsed time per iteration (s): 0.25 | learning rate: 7.080E-05 | global batch size: 256 | lm loss: 2.893634E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.147 | TFLOPs: 6.42 | +31: iteration 24400/ 37905 | consumed samples: 6246400 | consumed tokens: 12792627200 | elapsed time per iteration (s): 0.21 | learning rate: 7.073E-05 | global batch size: 256 | lm loss: 2.936408E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.163 | TFLOPs: 7.61 | +31: iteration 24410/ 37905 | consumed samples: 6248960 | consumed tokens: 12797870080 | elapsed time per iteration (s): 0.23 | learning rate: 7.067E-05 | global batch size: 256 | lm loss: 2.923497E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.415 | TFLOPs: 7.10 | +31: iteration 24420/ 37905 | consumed samples: 6251520 | consumed tokens: 12803112960 | elapsed time per iteration (s): 0.20 | learning rate: 7.060E-05 | global batch size: 256 | lm loss: 2.940979E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.552 | TFLOPs: 7.98 | +31: iteration 24430/ 37905 | consumed samples: 6254080 | consumed tokens: 12808355840 | elapsed time per iteration (s): 0.25 | learning rate: 7.053E-05 | global batch size: 256 | lm loss: 2.938013E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.812 | TFLOPs: 6.56 | +31: iteration 24440/ 37905 | consumed samples: 6256640 | consumed tokens: 12813598720 | elapsed time per iteration (s): 0.23 | learning rate: 7.046E-05 | global batch size: 256 | lm loss: 2.921252E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.729 | TFLOPs: 7.15 | +31: iteration 24450/ 37905 | consumed samples: 6259200 | consumed tokens: 12818841600 | elapsed time per iteration (s): 0.22 | learning rate: 7.040E-05 | global batch size: 256 | lm loss: 2.901908E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.924 | TFLOPs: 7.31 | +31: iteration 24460/ 37905 | consumed samples: 6261760 | consumed tokens: 12824084480 | elapsed time per iteration (s): 0.23 | learning rate: 7.033E-05 | global batch size: 256 | lm loss: 2.940944E+00 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.706 | TFLOPs: 7.01 | +31: iteration 24470/ 37905 | consumed samples: 6264320 | consumed tokens: 12829327360 | elapsed time per iteration (s): 0.22 | learning rate: 7.026E-05 | global batch size: 256 | lm loss: 2.912920E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.142 | TFLOPs: 7.33 | +31: iteration 24480/ 37905 | consumed samples: 6266880 | consumed tokens: 12834570240 | elapsed time per iteration (s): 0.20 | learning rate: 7.020E-05 | global batch size: 256 | lm loss: 2.925430E+00 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.803 | TFLOPs: 8.10 | +31: iteration 24490/ 37905 | consumed samples: 6269440 | consumed tokens: 12839813120 | elapsed time per iteration (s): 0.21 | learning rate: 7.013E-05 | global batch size: 256 | lm loss: 2.926060E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.934 | TFLOPs: 7.65 | +31: iteration 24500/ 37905 | consumed samples: 6272000 | consumed tokens: 12845056000 | elapsed time per iteration (s): 0.22 | learning rate: 7.006E-05 | global batch size: 256 | lm loss: 2.930952E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.035 | TFLOPs: 7.26 | +31: iteration 24510/ 37905 | consumed samples: 6274560 | consumed tokens: 12850298880 | elapsed time per iteration (s): 0.19 | learning rate: 7.000E-05 | global batch size: 256 | lm loss: 2.948119E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1331.995 | TFLOPs: 8.48 | +31: iteration 24520/ 37905 | consumed samples: 6277120 | consumed tokens: 12855541760 | elapsed time per iteration (s): 0.20 | learning rate: 6.993E-05 | global batch size: 256 | lm loss: 2.969515E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.328 | TFLOPs: 8.01 | +31: iteration 24530/ 37905 | consumed samples: 6279680 | consumed tokens: 12860784640 | elapsed time per iteration (s): 0.21 | learning rate: 6.986E-05 | global batch size: 256 | lm loss: 2.916422E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.249 | TFLOPs: 7.87 | +31: iteration 24540/ 37905 | consumed samples: 6282240 | consumed tokens: 12866027520 | elapsed time per iteration (s): 0.20 | learning rate: 6.980E-05 | global batch size: 256 | lm loss: 2.947039E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.980 | TFLOPs: 7.96 | +31: iteration 24550/ 37905 | consumed samples: 6284800 | consumed tokens: 12871270400 | elapsed time per iteration (s): 0.20 | learning rate: 6.973E-05 | global batch size: 256 | lm loss: 2.922931E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.018 | TFLOPs: 7.99 | +31: iteration 24560/ 37905 | consumed samples: 6287360 | consumed tokens: 12876513280 | elapsed time per iteration (s): 0.20 | learning rate: 6.966E-05 | global batch size: 256 | lm loss: 2.935407E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1299.535 | TFLOPs: 8.28 | +31: iteration 24570/ 37905 | consumed samples: 6289920 | consumed tokens: 12881756160 | elapsed time per iteration (s): 0.23 | learning rate: 6.960E-05 | global batch size: 256 | lm loss: 2.961347E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.673 | TFLOPs: 7.04 | +31: iteration 24580/ 37905 | consumed samples: 6292480 | consumed tokens: 12886999040 | elapsed time per iteration (s): 0.22 | learning rate: 6.953E-05 | global batch size: 256 | lm loss: 2.944097E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.033 | TFLOPs: 7.52 | +31: iteration 24590/ 37905 | consumed samples: 6295040 | consumed tokens: 12892241920 | elapsed time per iteration (s): 0.22 | learning rate: 6.946E-05 | global batch size: 256 | lm loss: 2.871029E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.780 | TFLOPs: 7.46 | +31: iteration 24600/ 37905 | consumed samples: 6297600 | consumed tokens: 12897484800 | elapsed time per iteration (s): 0.22 | learning rate: 6.940E-05 | global batch size: 256 | lm loss: 2.919765E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.379 | TFLOPs: 7.28 | +31: iteration 24610/ 37905 | consumed samples: 6300160 | consumed tokens: 12902727680 | elapsed time per iteration (s): 0.22 | learning rate: 6.933E-05 | global batch size: 256 | lm loss: 2.921976E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.573 | TFLOPs: 7.48 | +31: iteration 24620/ 37905 | consumed samples: 6302720 | consumed tokens: 12907970560 | elapsed time per iteration (s): 0.21 | learning rate: 6.926E-05 | global batch size: 256 | lm loss: 2.961204E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.472 | TFLOPs: 7.59 | +31: iteration 24630/ 37905 | consumed samples: 6305280 | consumed tokens: 12913213440 | elapsed time per iteration (s): 0.22 | learning rate: 6.920E-05 | global batch size: 256 | lm loss: 2.915308E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.631 | TFLOPs: 7.42 | +31: iteration 24640/ 37905 | consumed samples: 6307840 | consumed tokens: 12918456320 | elapsed time per iteration (s): 0.21 | learning rate: 6.913E-05 | global batch size: 256 | lm loss: 2.945792E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.121 | TFLOPs: 7.61 | +31: iteration 24650/ 37905 | consumed samples: 6310400 | consumed tokens: 12923699200 | elapsed time per iteration (s): 0.21 | learning rate: 6.906E-05 | global batch size: 256 | lm loss: 2.939107E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.298 | TFLOPs: 7.68 | +31: iteration 24660/ 37905 | consumed samples: 6312960 | consumed tokens: 12928942080 | elapsed time per iteration (s): 0.21 | learning rate: 6.900E-05 | global batch size: 256 | lm loss: 2.932577E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.891 | TFLOPs: 7.71 | +31: iteration 24670/ 37905 | consumed samples: 6315520 | consumed tokens: 12934184960 | elapsed time per iteration (s): 0.25 | learning rate: 6.893E-05 | global batch size: 256 | lm loss: 2.933504E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.185 | TFLOPs: 6.51 | +31: iteration 24680/ 37905 | consumed samples: 6318080 | consumed tokens: 12939427840 | elapsed time per iteration (s): 0.22 | learning rate: 6.886E-05 | global batch size: 256 | lm loss: 2.911738E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.248 | TFLOPs: 7.54 | +31: iteration 24690/ 37905 | consumed samples: 6320640 | consumed tokens: 12944670720 | elapsed time per iteration (s): 0.22 | learning rate: 6.880E-05 | global batch size: 256 | lm loss: 2.954438E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.181 | TFLOPs: 7.48 | +31: iteration 24700/ 37905 | consumed samples: 6323200 | consumed tokens: 12949913600 | elapsed time per iteration (s): 0.20 | learning rate: 6.873E-05 | global batch size: 256 | lm loss: 2.953098E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.040 | TFLOPs: 8.11 | +31: iteration 24710/ 37905 | consumed samples: 6325760 | consumed tokens: 12955156480 | elapsed time per iteration (s): 0.24 | learning rate: 6.867E-05 | global batch size: 256 | lm loss: 2.860042E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.373 | TFLOPs: 6.82 | +31: iteration 24720/ 37905 | consumed samples: 6328320 | consumed tokens: 12960399360 | elapsed time per iteration (s): 0.24 | learning rate: 6.860E-05 | global batch size: 256 | lm loss: 2.916684E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.231 | TFLOPs: 6.93 | +31: iteration 24730/ 37905 | consumed samples: 6330880 | consumed tokens: 12965642240 | elapsed time per iteration (s): 0.21 | learning rate: 6.853E-05 | global batch size: 256 | lm loss: 2.893095E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.725 | TFLOPs: 7.80 | +31: iteration 24740/ 37905 | consumed samples: 6333440 | consumed tokens: 12970885120 | elapsed time per iteration (s): 0.22 | learning rate: 6.847E-05 | global batch size: 256 | lm loss: 2.913908E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.714 | TFLOPs: 7.38 | +31: iteration 24750/ 37905 | consumed samples: 6336000 | consumed tokens: 12976128000 | elapsed time per iteration (s): 0.22 | learning rate: 6.840E-05 | global batch size: 256 | lm loss: 2.898258E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.061 | TFLOPs: 7.46 | +31: iteration 24760/ 37905 | consumed samples: 6338560 | consumed tokens: 12981370880 | elapsed time per iteration (s): 0.22 | learning rate: 6.833E-05 | global batch size: 256 | lm loss: 2.896731E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.844 | TFLOPs: 7.55 | +31: iteration 24770/ 37905 | consumed samples: 6341120 | consumed tokens: 12986613760 | elapsed time per iteration (s): 0.21 | learning rate: 6.827E-05 | global batch size: 256 | lm loss: 2.932644E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.186 | TFLOPs: 7.92 | +31: iteration 24780/ 37905 | consumed samples: 6343680 | consumed tokens: 12991856640 | elapsed time per iteration (s): 0.21 | learning rate: 6.820E-05 | global batch size: 256 | lm loss: 2.923205E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.338 | TFLOPs: 7.68 | +31: iteration 24790/ 37905 | consumed samples: 6346240 | consumed tokens: 12997099520 | elapsed time per iteration (s): 0.20 | learning rate: 6.814E-05 | global batch size: 256 | lm loss: 2.921945E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1273.102 | TFLOPs: 8.11 | +31: iteration 24800/ 37905 | consumed samples: 6348800 | consumed tokens: 13002342400 | elapsed time per iteration (s): 0.20 | learning rate: 6.807E-05 | global batch size: 256 | lm loss: 2.911559E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.691 | TFLOPs: 8.14 | +31: iteration 24810/ 37905 | consumed samples: 6351360 | consumed tokens: 13007585280 | elapsed time per iteration (s): 0.25 | learning rate: 6.800E-05 | global batch size: 256 | lm loss: 2.941900E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1026.387 | TFLOPs: 6.54 | +31: iteration 24820/ 37905 | consumed samples: 6353920 | consumed tokens: 13012828160 | elapsed time per iteration (s): 0.21 | learning rate: 6.794E-05 | global batch size: 256 | lm loss: 2.931210E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.752 | TFLOPs: 7.88 | +31: iteration 24830/ 37905 | consumed samples: 6356480 | consumed tokens: 13018071040 | elapsed time per iteration (s): 0.21 | learning rate: 6.787E-05 | global batch size: 256 | lm loss: 2.926864E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.474 | TFLOPs: 7.73 | +31: iteration 24840/ 37905 | consumed samples: 6359040 | consumed tokens: 13023313920 | elapsed time per iteration (s): 0.23 | learning rate: 6.781E-05 | global batch size: 256 | lm loss: 2.897121E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.359 | TFLOPs: 7.05 | +31: iteration 24850/ 37905 | consumed samples: 6361600 | consumed tokens: 13028556800 | elapsed time per iteration (s): 0.23 | learning rate: 6.774E-05 | global batch size: 256 | lm loss: 2.925627E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.706 | TFLOPs: 7.19 | +31: iteration 24860/ 37905 | consumed samples: 6364160 | consumed tokens: 13033799680 | elapsed time per iteration (s): 0.20 | learning rate: 6.767E-05 | global batch size: 256 | lm loss: 2.868253E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1259.944 | TFLOPs: 8.02 | +31: iteration 24870/ 37905 | consumed samples: 6366720 | consumed tokens: 13039042560 | elapsed time per iteration (s): 0.21 | learning rate: 6.761E-05 | global batch size: 256 | lm loss: 2.922070E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.044 | TFLOPs: 7.94 | +31: iteration 24880/ 37905 | consumed samples: 6369280 | consumed tokens: 13044285440 | elapsed time per iteration (s): 0.20 | learning rate: 6.754E-05 | global batch size: 256 | lm loss: 2.902873E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.741 | TFLOPs: 8.09 | +31: iteration 24890/ 37905 | consumed samples: 6371840 | consumed tokens: 13049528320 | elapsed time per iteration (s): 0.20 | learning rate: 6.748E-05 | global batch size: 256 | lm loss: 2.915866E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1303.240 | TFLOPs: 8.30 | +31: iteration 24900/ 37905 | consumed samples: 6374400 | consumed tokens: 13054771200 | elapsed time per iteration (s): 0.22 | learning rate: 6.741E-05 | global batch size: 256 | lm loss: 2.893734E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.034 | TFLOPs: 7.35 | +31: iteration 24910/ 37905 | consumed samples: 6376960 | consumed tokens: 13060014080 | elapsed time per iteration (s): 0.21 | learning rate: 6.735E-05 | global batch size: 256 | lm loss: 2.899566E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.341 | TFLOPs: 7.90 | +31: iteration 24920/ 37905 | consumed samples: 6379520 | consumed tokens: 13065256960 | elapsed time per iteration (s): 0.18 | learning rate: 6.728E-05 | global batch size: 256 | lm loss: 2.916758E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1392.771 | TFLOPs: 8.87 | +31: iteration 24930/ 37905 | consumed samples: 6382080 | consumed tokens: 13070499840 | elapsed time per iteration (s): 0.20 | learning rate: 6.721E-05 | global batch size: 256 | lm loss: 2.917433E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.187 | TFLOPs: 7.99 | +31: iteration 24940/ 37905 | consumed samples: 6384640 | consumed tokens: 13075742720 | elapsed time per iteration (s): 0.23 | learning rate: 6.715E-05 | global batch size: 256 | lm loss: 2.907431E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.069 | TFLOPs: 7.07 | +31: iteration 24950/ 37905 | consumed samples: 6387200 | consumed tokens: 13080985600 | elapsed time per iteration (s): 0.21 | learning rate: 6.708E-05 | global batch size: 256 | lm loss: 2.921008E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.431 | TFLOPs: 7.73 | +31: iteration 24960/ 37905 | consumed samples: 6389760 | consumed tokens: 13086228480 | elapsed time per iteration (s): 0.26 | learning rate: 6.702E-05 | global batch size: 256 | lm loss: 2.906432E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 988.071 | TFLOPs: 6.29 | +31: iteration 24970/ 37905 | consumed samples: 6392320 | consumed tokens: 13091471360 | elapsed time per iteration (s): 0.22 | learning rate: 6.695E-05 | global batch size: 256 | lm loss: 2.889389E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.836 | TFLOPs: 7.50 | +31: iteration 24980/ 37905 | consumed samples: 6394880 | consumed tokens: 13096714240 | elapsed time per iteration (s): 0.21 | learning rate: 6.689E-05 | global batch size: 256 | lm loss: 2.895898E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.298 | TFLOPs: 7.85 | +31: iteration 24990/ 37905 | consumed samples: 6397440 | consumed tokens: 13101957120 | elapsed time per iteration (s): 0.24 | learning rate: 6.682E-05 | global batch size: 256 | lm loss: 2.917601E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.561 | TFLOPs: 6.74 | +31: iteration 25000/ 37905 | consumed samples: 6400000 | consumed tokens: 13107200000 | elapsed time per iteration (s): 0.21 | learning rate: 6.676E-05 | global batch size: 256 | lm loss: 2.912720E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.362 | TFLOPs: 7.67 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 25000 | lm loss value: 2.837725E+00 | lm loss PPL: 1.707687E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 25000 to checkpoints_83m + 0: [2022-11-24 15:41:46,281] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step25000 is begin to save! + 0: [2022-11-24 15:41:46,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,365] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,377] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,399] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,410] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,421] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,432] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,443] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,443] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,454] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:41:46,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:41:46,478] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step25000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:41:46,478] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:41:46,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:41:46,546] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step25000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:41:46,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 3: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +10: [2022-11-24 15:41:46,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:41:46,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 0: [2022-11-24 15:41:46,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +25: [2022-11-24 15:41:46,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:41:46,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +18: [2022-11-24 15:41:46,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:41:46,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +17: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 15:41:46,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 0: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:41:46,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +10: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +22: [2022-11-24 15:41:46,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:41:46,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +15: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:41:46,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:41:46,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +14: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +25: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +30: [2022-11-24 15:41:46,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +19: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +18: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +24: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:41:46,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:41:46,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 3: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 5: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:41:46,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 0: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:41:46,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:41:46,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:41:46,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +12: [2022-11-24 15:41:46,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +22: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:41:46,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:41:46,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:41:46,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:41:46,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +15: [2022-11-24 15:41:46,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +25: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:41:46,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +19: [2022-11-24 15:41:46,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:41:46,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +14: [2022-11-24 15:41:46,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:41:46,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +18: [2022-11-24 15:41:46,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +24: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:41:46,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +28: [2022-11-24 15:41:46,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 3: [2022-11-24 15:41:46,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:41:46,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:41:46,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 5: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 0: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:41:46,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:41:46,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:41:46,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +10: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:41:46,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +22: [2022-11-24 15:41:46,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:41:46,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:41:46,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +15: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +25: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:41:46,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:41:46,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +14: [2022-11-24 15:41:46,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +19: [2022-11-24 15:41:46,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:41:46,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:41:46,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +18: [2022-11-24 15:41:46,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +24: [2022-11-24 15:41:46,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:41:46,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:41:46,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:41:46,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +17: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:41:46,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 0: [2022-11-24 15:41:46,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:41:46,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +10: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:41:46,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +22: [2022-11-24 15:41:46,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:41:46,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +15: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:41:46,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +25: [2022-11-24 15:41:46,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:41:46,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +14: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +19: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +18: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,587] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,587] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +24: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:41:46,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:41:46,588] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 5: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:41:46,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +17: [2022-11-24 15:41:46,589] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +10: [2022-11-24 15:41:46,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,590] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,590] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:41:46,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,591] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +22: [2022-11-24 15:41:46,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:41:46,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:41:46,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,592] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +15: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +25: [2022-11-24 15:41:46,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:41:46,593] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +14: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +18: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +19: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +24: [2022-11-24 15:41:46,594] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,594] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,595] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,595] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,595] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 5: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 3: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:41:46,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,596] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 9: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +17: [2022-11-24 15:41:46,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:41:46,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +10: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:41:46,597] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,597] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +12: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:41:46,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:41:46,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +30: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +22: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,598] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,598] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:41:46,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,599] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +25: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:41:46,600] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:41:46,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +26: [2022-11-24 15:41:46,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +19: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,601] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +14: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +18: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +24: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 0: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +12: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +24: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +31: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +31: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +21: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +19: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +21: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +18: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,602] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +13: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +23: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,602] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +20: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +26: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 5: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +28: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 1: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +14: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +13: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 4: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +20: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +24: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 7: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +17: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +11: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +10: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +30: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +19: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 3: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 6: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 8: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +26: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +11: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +28: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +10: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +19: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +22: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +28: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +30: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +15: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +23: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +16: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +22: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +23: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +15: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +29: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:41:46,603] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +29: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 2: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +16: [2022-11-24 15:41:46,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:41:46,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:41:46,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,604] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step25000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:41:46,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! +27: [2022-11-24 15:41:46,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step25000 is ready now! + 0: successfully saved checkpoint at iteration 25000 to checkpoints_83m +31: time (ms) | save-checkpoint: 328.65 +31: iteration 25010/ 37905 | consumed samples: 6402560 | consumed tokens: 13112442880 | elapsed time per iteration (s): 0.24 | learning rate: 6.669E-05 | global batch size: 256 | lm loss: 2.906147E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.903 | TFLOPs: 6.89 | +31: iteration 25020/ 37905 | consumed samples: 6405120 | consumed tokens: 13117685760 | elapsed time per iteration (s): 0.23 | learning rate: 6.662E-05 | global batch size: 256 | lm loss: 2.909193E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.833 | TFLOPs: 7.11 | +31: iteration 25030/ 37905 | consumed samples: 6407680 | consumed tokens: 13122928640 | elapsed time per iteration (s): 0.24 | learning rate: 6.656E-05 | global batch size: 256 | lm loss: 2.915244E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.965 | TFLOPs: 6.79 | +31: iteration 25040/ 37905 | consumed samples: 6410240 | consumed tokens: 13128171520 | elapsed time per iteration (s): 0.22 | learning rate: 6.649E-05 | global batch size: 256 | lm loss: 2.925357E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.374 | TFLOPs: 7.50 | +31: iteration 25050/ 37905 | consumed samples: 6412800 | consumed tokens: 13133414400 | elapsed time per iteration (s): 0.22 | learning rate: 6.643E-05 | global batch size: 256 | lm loss: 2.938537E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.679 | TFLOPs: 7.47 | +31: iteration 25060/ 37905 | consumed samples: 6415360 | consumed tokens: 13138657280 | elapsed time per iteration (s): 0.23 | learning rate: 6.636E-05 | global batch size: 256 | lm loss: 2.917932E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.343 | TFLOPs: 7.14 | +31: iteration 25070/ 37905 | consumed samples: 6417920 | consumed tokens: 13143900160 | elapsed time per iteration (s): 0.22 | learning rate: 6.630E-05 | global batch size: 256 | lm loss: 2.907536E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.760 | TFLOPs: 7.51 | +31: iteration 25080/ 37905 | consumed samples: 6420480 | consumed tokens: 13149143040 | elapsed time per iteration (s): 0.20 | learning rate: 6.623E-05 | global batch size: 256 | lm loss: 2.935399E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1299.086 | TFLOPs: 8.27 | +31: iteration 25090/ 37905 | consumed samples: 6423040 | consumed tokens: 13154385920 | elapsed time per iteration (s): 0.24 | learning rate: 6.617E-05 | global batch size: 256 | lm loss: 2.919148E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.435 | TFLOPs: 6.71 | +31: iteration 25100/ 37905 | consumed samples: 6425600 | consumed tokens: 13159628800 | elapsed time per iteration (s): 0.23 | learning rate: 6.610E-05 | global batch size: 256 | lm loss: 2.924665E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.503 | TFLOPs: 6.95 | +31: iteration 25110/ 37905 | consumed samples: 6428160 | consumed tokens: 13164871680 | elapsed time per iteration (s): 0.22 | learning rate: 6.604E-05 | global batch size: 256 | lm loss: 2.910525E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.743 | TFLOPs: 7.35 | +31: iteration 25120/ 37905 | consumed samples: 6430720 | consumed tokens: 13170114560 | elapsed time per iteration (s): 0.21 | learning rate: 6.597E-05 | global batch size: 256 | lm loss: 2.890563E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.504 | TFLOPs: 7.75 | +31: iteration 25130/ 37905 | consumed samples: 6433280 | consumed tokens: 13175357440 | elapsed time per iteration (s): 0.19 | learning rate: 6.591E-05 | global batch size: 256 | lm loss: 2.914683E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1319.124 | TFLOPs: 8.40 | +31: iteration 25140/ 37905 | consumed samples: 6435840 | consumed tokens: 13180600320 | elapsed time per iteration (s): 0.21 | learning rate: 6.584E-05 | global batch size: 256 | lm loss: 2.906734E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.273 | TFLOPs: 7.59 | +31: iteration 25150/ 37905 | consumed samples: 6438400 | consumed tokens: 13185843200 | elapsed time per iteration (s): 0.20 | learning rate: 6.578E-05 | global batch size: 256 | lm loss: 2.933577E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.618 | TFLOPs: 8.21 | +31: iteration 25160/ 37905 | consumed samples: 6440960 | consumed tokens: 13191086080 | elapsed time per iteration (s): 0.26 | learning rate: 6.571E-05 | global batch size: 256 | lm loss: 2.938639E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 971.759 | TFLOPs: 6.19 | +31: iteration 25170/ 37905 | consumed samples: 6443520 | consumed tokens: 13196328960 | elapsed time per iteration (s): 0.21 | learning rate: 6.565E-05 | global batch size: 256 | lm loss: 2.920378E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.746 | TFLOPs: 7.80 | +31: iteration 25180/ 37905 | consumed samples: 6446080 | consumed tokens: 13201571840 | elapsed time per iteration (s): 0.25 | learning rate: 6.558E-05 | global batch size: 256 | lm loss: 2.901940E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.948 | TFLOPs: 6.44 | +31: iteration 25190/ 37905 | consumed samples: 6448640 | consumed tokens: 13206814720 | elapsed time per iteration (s): 0.23 | learning rate: 6.552E-05 | global batch size: 256 | lm loss: 2.934986E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.577 | TFLOPs: 7.08 | +31: iteration 25200/ 37905 | consumed samples: 6451200 | consumed tokens: 13212057600 | elapsed time per iteration (s): 0.22 | learning rate: 6.545E-05 | global batch size: 256 | lm loss: 2.920924E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.395 | TFLOPs: 7.47 | +31: iteration 25210/ 37905 | consumed samples: 6453760 | consumed tokens: 13217300480 | elapsed time per iteration (s): 0.20 | learning rate: 6.539E-05 | global batch size: 256 | lm loss: 2.928456E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1301.185 | TFLOPs: 8.29 | +31: iteration 25220/ 37905 | consumed samples: 6456320 | consumed tokens: 13222543360 | elapsed time per iteration (s): 0.20 | learning rate: 6.532E-05 | global batch size: 256 | lm loss: 2.934520E+00 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.716 | TFLOPs: 8.06 | +31: iteration 25230/ 37905 | consumed samples: 6458880 | consumed tokens: 13227786240 | elapsed time per iteration (s): 0.20 | learning rate: 6.526E-05 | global batch size: 256 | lm loss: 2.901588E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.563 | TFLOPs: 8.07 | +31: iteration 25240/ 37905 | consumed samples: 6461440 | consumed tokens: 13233029120 | elapsed time per iteration (s): 0.23 | learning rate: 6.519E-05 | global batch size: 256 | lm loss: 2.918107E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.001 | TFLOPs: 7.11 | +31: iteration 25250/ 37905 | consumed samples: 6464000 | consumed tokens: 13238272000 | elapsed time per iteration (s): 0.20 | learning rate: 6.513E-05 | global batch size: 256 | lm loss: 2.907105E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.313 | TFLOPs: 8.10 | +31: iteration 25260/ 37905 | consumed samples: 6466560 | consumed tokens: 13243514880 | elapsed time per iteration (s): 0.23 | learning rate: 6.506E-05 | global batch size: 256 | lm loss: 2.909864E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.203 | TFLOPs: 7.01 | +31: iteration 25270/ 37905 | consumed samples: 6469120 | consumed tokens: 13248757760 | elapsed time per iteration (s): 0.22 | learning rate: 6.500E-05 | global batch size: 256 | lm loss: 2.937477E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.638 | TFLOPs: 7.27 | +31: iteration 25280/ 37905 | consumed samples: 6471680 | consumed tokens: 13254000640 | elapsed time per iteration (s): 0.22 | learning rate: 6.494E-05 | global batch size: 256 | lm loss: 2.936679E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.999 | TFLOPs: 7.29 | +31: iteration 25290/ 37905 | consumed samples: 6474240 | consumed tokens: 13259243520 | elapsed time per iteration (s): 0.22 | learning rate: 6.487E-05 | global batch size: 256 | lm loss: 2.857469E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.287 | TFLOPs: 7.49 | +31: iteration 25300/ 37905 | consumed samples: 6476800 | consumed tokens: 13264486400 | elapsed time per iteration (s): 0.23 | learning rate: 6.481E-05 | global batch size: 256 | lm loss: 2.922395E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.496 | TFLOPs: 7.08 | +31: iteration 25310/ 37905 | consumed samples: 6479360 | consumed tokens: 13269729280 | elapsed time per iteration (s): 0.25 | learning rate: 6.474E-05 | global batch size: 256 | lm loss: 2.907404E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1013.106 | TFLOPs: 6.45 | +31: iteration 25320/ 37905 | consumed samples: 6481920 | consumed tokens: 13274972160 | elapsed time per iteration (s): 0.22 | learning rate: 6.468E-05 | global batch size: 256 | lm loss: 2.912777E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.596 | TFLOPs: 7.48 | +31: iteration 25330/ 37905 | consumed samples: 6484480 | consumed tokens: 13280215040 | elapsed time per iteration (s): 0.25 | learning rate: 6.461E-05 | global batch size: 256 | lm loss: 2.916606E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1027.581 | TFLOPs: 6.54 | +31: iteration 25340/ 37905 | consumed samples: 6487040 | consumed tokens: 13285457920 | elapsed time per iteration (s): 0.21 | learning rate: 6.455E-05 | global batch size: 256 | lm loss: 2.921305E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.471 | TFLOPs: 7.76 | +31: iteration 25350/ 37905 | consumed samples: 6489600 | consumed tokens: 13290700800 | elapsed time per iteration (s): 0.23 | learning rate: 6.448E-05 | global batch size: 256 | lm loss: 2.905739E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.662 | TFLOPs: 7.04 | +31: iteration 25360/ 37905 | consumed samples: 6492160 | consumed tokens: 13295943680 | elapsed time per iteration (s): 0.24 | learning rate: 6.442E-05 | global batch size: 256 | lm loss: 2.910256E+00 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.407 | TFLOPs: 6.82 | +31: iteration 25370/ 37905 | consumed samples: 6494720 | consumed tokens: 13301186560 | elapsed time per iteration (s): 0.21 | learning rate: 6.436E-05 | global batch size: 256 | lm loss: 2.895684E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.435 | TFLOPs: 7.61 | +31: iteration 25380/ 37905 | consumed samples: 6497280 | consumed tokens: 13306429440 | elapsed time per iteration (s): 0.23 | learning rate: 6.429E-05 | global batch size: 256 | lm loss: 2.933829E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.859 | TFLOPs: 7.00 | +31: iteration 25390/ 37905 | consumed samples: 6499840 | consumed tokens: 13311672320 | elapsed time per iteration (s): 0.22 | learning rate: 6.423E-05 | global batch size: 256 | lm loss: 2.952704E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.077 | TFLOPs: 7.45 | +31: iteration 25400/ 37905 | consumed samples: 6502400 | consumed tokens: 13316915200 | elapsed time per iteration (s): 0.24 | learning rate: 6.416E-05 | global batch size: 256 | lm loss: 2.925542E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.120 | TFLOPs: 6.84 | +31: iteration 25410/ 37905 | consumed samples: 6504960 | consumed tokens: 13322158080 | elapsed time per iteration (s): 0.22 | learning rate: 6.410E-05 | global batch size: 256 | lm loss: 2.885635E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.211 | TFLOPs: 7.45 | +31: iteration 25420/ 37905 | consumed samples: 6507520 | consumed tokens: 13327400960 | elapsed time per iteration (s): 0.23 | learning rate: 6.403E-05 | global batch size: 256 | lm loss: 2.892264E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.865 | TFLOPs: 7.20 | +31: iteration 25430/ 37905 | consumed samples: 6510080 | consumed tokens: 13332643840 | elapsed time per iteration (s): 0.25 | learning rate: 6.397E-05 | global batch size: 256 | lm loss: 2.935973E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.179 | TFLOPs: 6.62 | +31: iteration 25440/ 37905 | consumed samples: 6512640 | consumed tokens: 13337886720 | elapsed time per iteration (s): 0.23 | learning rate: 6.391E-05 | global batch size: 256 | lm loss: 2.906710E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.970 | TFLOPs: 7.19 | +31: iteration 25450/ 37905 | consumed samples: 6515200 | consumed tokens: 13343129600 | elapsed time per iteration (s): 0.19 | learning rate: 6.384E-05 | global batch size: 256 | lm loss: 2.906228E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1331.332 | TFLOPs: 8.48 | +31: iteration 25460/ 37905 | consumed samples: 6517760 | consumed tokens: 13348372480 | elapsed time per iteration (s): 0.23 | learning rate: 6.378E-05 | global batch size: 256 | lm loss: 2.940823E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.931 | TFLOPs: 7.01 | +31: iteration 25470/ 37905 | consumed samples: 6520320 | consumed tokens: 13353615360 | elapsed time per iteration (s): 0.19 | learning rate: 6.371E-05 | global batch size: 256 | lm loss: 2.920073E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.635 | TFLOPs: 8.58 | +31: iteration 25480/ 37905 | consumed samples: 6522880 | consumed tokens: 13358858240 | elapsed time per iteration (s): 0.22 | learning rate: 6.365E-05 | global batch size: 256 | lm loss: 2.923966E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.051 | TFLOPs: 7.31 | +31: iteration 25490/ 37905 | consumed samples: 6525440 | consumed tokens: 13364101120 | elapsed time per iteration (s): 0.23 | learning rate: 6.359E-05 | global batch size: 256 | lm loss: 2.890358E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.438 | TFLOPs: 7.05 | +31: iteration 25500/ 37905 | consumed samples: 6528000 | consumed tokens: 13369344000 | elapsed time per iteration (s): 0.20 | learning rate: 6.352E-05 | global batch size: 256 | lm loss: 2.913818E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1302.133 | TFLOPs: 8.29 | +31: iteration 25510/ 37905 | consumed samples: 6530560 | consumed tokens: 13374586880 | elapsed time per iteration (s): 0.23 | learning rate: 6.346E-05 | global batch size: 256 | lm loss: 2.880674E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.931 | TFLOPs: 7.18 | +31: iteration 25520/ 37905 | consumed samples: 6533120 | consumed tokens: 13379829760 | elapsed time per iteration (s): 0.27 | learning rate: 6.340E-05 | global batch size: 256 | lm loss: 2.901005E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 942.906 | TFLOPs: 6.01 | +31: iteration 25530/ 37905 | consumed samples: 6535680 | consumed tokens: 13385072640 | elapsed time per iteration (s): 0.21 | learning rate: 6.333E-05 | global batch size: 256 | lm loss: 2.919332E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.347 | TFLOPs: 7.64 | +31: iteration 25540/ 37905 | consumed samples: 6538240 | consumed tokens: 13390315520 | elapsed time per iteration (s): 0.22 | learning rate: 6.327E-05 | global batch size: 256 | lm loss: 2.911992E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.697 | TFLOPs: 7.55 | +31: iteration 25550/ 37905 | consumed samples: 6540800 | consumed tokens: 13395558400 | elapsed time per iteration (s): 0.20 | learning rate: 6.320E-05 | global batch size: 256 | lm loss: 2.912333E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.766 | TFLOPs: 8.25 | +31: iteration 25560/ 37905 | consumed samples: 6543360 | consumed tokens: 13400801280 | elapsed time per iteration (s): 0.24 | learning rate: 6.314E-05 | global batch size: 256 | lm loss: 2.924894E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.640 | TFLOPs: 6.90 | +31: iteration 25570/ 37905 | consumed samples: 6545920 | consumed tokens: 13406044160 | elapsed time per iteration (s): 0.21 | learning rate: 6.308E-05 | global batch size: 256 | lm loss: 2.902958E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.532 | TFLOPs: 7.81 | +31: iteration 25580/ 37905 | consumed samples: 6548480 | consumed tokens: 13411287040 | elapsed time per iteration (s): 0.23 | learning rate: 6.301E-05 | global batch size: 256 | lm loss: 2.889852E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.591 | TFLOPs: 7.19 | +31: iteration 25590/ 37905 | consumed samples: 6551040 | consumed tokens: 13416529920 | elapsed time per iteration (s): 0.22 | learning rate: 6.295E-05 | global batch size: 256 | lm loss: 2.898664E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.460 | TFLOPs: 7.33 | +31: iteration 25600/ 37905 | consumed samples: 6553600 | consumed tokens: 13421772800 | elapsed time per iteration (s): 0.20 | learning rate: 6.289E-05 | global batch size: 256 | lm loss: 2.893307E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1298.492 | TFLOPs: 8.27 | +31: iteration 25610/ 37905 | consumed samples: 6556160 | consumed tokens: 13427015680 | elapsed time per iteration (s): 0.22 | learning rate: 6.282E-05 | global batch size: 256 | lm loss: 2.913190E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.457 | TFLOPs: 7.26 | +31: iteration 25620/ 37905 | consumed samples: 6558720 | consumed tokens: 13432258560 | elapsed time per iteration (s): 0.20 | learning rate: 6.276E-05 | global batch size: 256 | lm loss: 2.943976E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.056 | TFLOPs: 8.13 | +31: iteration 25630/ 37905 | consumed samples: 6561280 | consumed tokens: 13437501440 | elapsed time per iteration (s): 0.21 | learning rate: 6.270E-05 | global batch size: 256 | lm loss: 2.941600E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.971 | TFLOPs: 7.81 | +31: iteration 25640/ 37905 | consumed samples: 6563840 | consumed tokens: 13442744320 | elapsed time per iteration (s): 0.20 | learning rate: 6.263E-05 | global batch size: 256 | lm loss: 2.913001E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.128 | TFLOPs: 8.10 | +31: iteration 25650/ 37905 | consumed samples: 6566400 | consumed tokens: 13447987200 | elapsed time per iteration (s): 0.21 | learning rate: 6.257E-05 | global batch size: 256 | lm loss: 2.926619E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1230.198 | TFLOPs: 7.83 | +31: iteration 25660/ 37905 | consumed samples: 6568960 | consumed tokens: 13453230080 | elapsed time per iteration (s): 0.20 | learning rate: 6.250E-05 | global batch size: 256 | lm loss: 2.932463E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.764 | TFLOPs: 8.11 | +31: iteration 25670/ 37905 | consumed samples: 6571520 | consumed tokens: 13458472960 | elapsed time per iteration (s): 0.21 | learning rate: 6.244E-05 | global batch size: 256 | lm loss: 2.926364E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.912 | TFLOPs: 7.76 | +31: iteration 25680/ 37905 | consumed samples: 6574080 | consumed tokens: 13463715840 | elapsed time per iteration (s): 0.22 | learning rate: 6.238E-05 | global batch size: 256 | lm loss: 2.909223E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.894 | TFLOPs: 7.38 | +31: iteration 25690/ 37905 | consumed samples: 6576640 | consumed tokens: 13468958720 | elapsed time per iteration (s): 0.23 | learning rate: 6.231E-05 | global batch size: 256 | lm loss: 2.916858E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.311 | TFLOPs: 7.03 | +31: iteration 25700/ 37905 | consumed samples: 6579200 | consumed tokens: 13474201600 | elapsed time per iteration (s): 0.22 | learning rate: 6.225E-05 | global batch size: 256 | lm loss: 2.940036E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.704 | TFLOPs: 7.51 | +31: iteration 25710/ 37905 | consumed samples: 6581760 | consumed tokens: 13479444480 | elapsed time per iteration (s): 0.22 | learning rate: 6.219E-05 | global batch size: 256 | lm loss: 2.881241E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.573 | TFLOPs: 7.31 | +31: iteration 25720/ 37905 | consumed samples: 6584320 | consumed tokens: 13484687360 | elapsed time per iteration (s): 0.22 | learning rate: 6.213E-05 | global batch size: 256 | lm loss: 2.916381E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.767 | TFLOPs: 7.28 | +31: iteration 25730/ 37905 | consumed samples: 6586880 | consumed tokens: 13489930240 | elapsed time per iteration (s): 0.25 | learning rate: 6.206E-05 | global batch size: 256 | lm loss: 2.912803E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.449 | TFLOPs: 6.51 | +31: iteration 25740/ 37905 | consumed samples: 6589440 | consumed tokens: 13495173120 | elapsed time per iteration (s): 0.23 | learning rate: 6.200E-05 | global batch size: 256 | lm loss: 2.921832E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.765 | TFLOPs: 7.09 | +31: iteration 25750/ 37905 | consumed samples: 6592000 | consumed tokens: 13500416000 | elapsed time per iteration (s): 0.20 | learning rate: 6.194E-05 | global batch size: 256 | lm loss: 2.920025E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.949 | TFLOPs: 7.97 | +31: iteration 25760/ 37905 | consumed samples: 6594560 | consumed tokens: 13505658880 | elapsed time per iteration (s): 0.20 | learning rate: 6.187E-05 | global batch size: 256 | lm loss: 2.943366E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.883 | TFLOPs: 8.16 | +31: iteration 25770/ 37905 | consumed samples: 6597120 | consumed tokens: 13510901760 | elapsed time per iteration (s): 0.23 | learning rate: 6.181E-05 | global batch size: 256 | lm loss: 2.917719E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.313 | TFLOPs: 7.21 | +31: iteration 25780/ 37905 | consumed samples: 6599680 | consumed tokens: 13516144640 | elapsed time per iteration (s): 0.21 | learning rate: 6.175E-05 | global batch size: 256 | lm loss: 2.904951E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.773 | TFLOPs: 7.66 | +31: iteration 25790/ 37905 | consumed samples: 6602240 | consumed tokens: 13521387520 | elapsed time per iteration (s): 0.20 | learning rate: 6.168E-05 | global batch size: 256 | lm loss: 2.943557E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.505 | TFLOPs: 8.00 | +31: iteration 25800/ 37905 | consumed samples: 6604800 | consumed tokens: 13526630400 | elapsed time per iteration (s): 0.22 | learning rate: 6.162E-05 | global batch size: 256 | lm loss: 2.913613E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.415 | TFLOPs: 7.45 | +31: iteration 25810/ 37905 | consumed samples: 6607360 | consumed tokens: 13531873280 | elapsed time per iteration (s): 0.23 | learning rate: 6.156E-05 | global batch size: 256 | lm loss: 2.939414E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.601 | TFLOPs: 7.16 | +31: iteration 25820/ 37905 | consumed samples: 6609920 | consumed tokens: 13537116160 | elapsed time per iteration (s): 0.21 | learning rate: 6.150E-05 | global batch size: 256 | lm loss: 2.935185E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1214.882 | TFLOPs: 7.74 | +31: iteration 25830/ 37905 | consumed samples: 6612480 | consumed tokens: 13542359040 | elapsed time per iteration (s): 0.23 | learning rate: 6.143E-05 | global batch size: 256 | lm loss: 2.918923E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.250 | TFLOPs: 7.15 | +31: iteration 25840/ 37905 | consumed samples: 6615040 | consumed tokens: 13547601920 | elapsed time per iteration (s): 0.23 | learning rate: 6.137E-05 | global batch size: 256 | lm loss: 2.912763E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.615 | TFLOPs: 7.00 | +31: iteration 25850/ 37905 | consumed samples: 6617600 | consumed tokens: 13552844800 | elapsed time per iteration (s): 0.21 | learning rate: 6.131E-05 | global batch size: 256 | lm loss: 2.935788E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.681 | TFLOPs: 7.73 | +31: iteration 25860/ 37905 | consumed samples: 6620160 | consumed tokens: 13558087680 | elapsed time per iteration (s): 0.26 | learning rate: 6.124E-05 | global batch size: 256 | lm loss: 2.931997E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 974.964 | TFLOPs: 6.21 | +31: iteration 25870/ 37905 | consumed samples: 6622720 | consumed tokens: 13563330560 | elapsed time per iteration (s): 0.21 | learning rate: 6.118E-05 | global batch size: 256 | lm loss: 2.915153E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.918 | TFLOPs: 7.90 | +31: iteration 25880/ 37905 | consumed samples: 6625280 | consumed tokens: 13568573440 | elapsed time per iteration (s): 0.21 | learning rate: 6.112E-05 | global batch size: 256 | lm loss: 2.891763E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.629 | TFLOPs: 7.91 | +31: iteration 25890/ 37905 | consumed samples: 6627840 | consumed tokens: 13573816320 | elapsed time per iteration (s): 0.23 | learning rate: 6.106E-05 | global batch size: 256 | lm loss: 2.890042E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.418 | TFLOPs: 7.15 | +31: iteration 25900/ 37905 | consumed samples: 6630400 | consumed tokens: 13579059200 | elapsed time per iteration (s): 0.22 | learning rate: 6.099E-05 | global batch size: 256 | lm loss: 2.921474E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.867 | TFLOPs: 7.33 | +31: iteration 25910/ 37905 | consumed samples: 6632960 | consumed tokens: 13584302080 | elapsed time per iteration (s): 0.19 | learning rate: 6.093E-05 | global batch size: 256 | lm loss: 2.926934E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.530 | TFLOPs: 8.54 | +31: iteration 25920/ 37905 | consumed samples: 6635520 | consumed tokens: 13589544960 | elapsed time per iteration (s): 0.21 | learning rate: 6.087E-05 | global batch size: 256 | lm loss: 2.906027E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.881 | TFLOPs: 7.83 | +31: iteration 25930/ 37905 | consumed samples: 6638080 | consumed tokens: 13594787840 | elapsed time per iteration (s): 0.21 | learning rate: 6.081E-05 | global batch size: 256 | lm loss: 2.922752E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.376 | TFLOPs: 7.86 | +31: iteration 25940/ 37905 | consumed samples: 6640640 | consumed tokens: 13600030720 | elapsed time per iteration (s): 0.22 | learning rate: 6.074E-05 | global batch size: 256 | lm loss: 2.902089E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.263 | TFLOPs: 7.50 | +31: iteration 25950/ 37905 | consumed samples: 6643200 | consumed tokens: 13605273600 | elapsed time per iteration (s): 0.21 | learning rate: 6.068E-05 | global batch size: 256 | lm loss: 2.928373E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.241 | TFLOPs: 7.71 | +31: iteration 25960/ 37905 | consumed samples: 6645760 | consumed tokens: 13610516480 | elapsed time per iteration (s): 0.21 | learning rate: 6.062E-05 | global batch size: 256 | lm loss: 2.904076E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.735 | TFLOPs: 7.68 | +31: iteration 25970/ 37905 | consumed samples: 6648320 | consumed tokens: 13615759360 | elapsed time per iteration (s): 0.20 | learning rate: 6.056E-05 | global batch size: 256 | lm loss: 2.921170E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.868 | TFLOPs: 8.36 | +31: iteration 25980/ 37905 | consumed samples: 6650880 | consumed tokens: 13621002240 | elapsed time per iteration (s): 0.22 | learning rate: 6.049E-05 | global batch size: 256 | lm loss: 2.891739E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.547 | TFLOPs: 7.25 | +31: iteration 25990/ 37905 | consumed samples: 6653440 | consumed tokens: 13626245120 | elapsed time per iteration (s): 0.19 | learning rate: 6.043E-05 | global batch size: 256 | lm loss: 2.931208E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1341.198 | TFLOPs: 8.54 | + 0: [2022-11-24 15:45:25,799] [INFO] [logging.py:68:log_dist] [Rank 0] step=26000, skipped=0, lr=[6.0369830292178765e-05, 6.0369830292178765e-05, 6.0369830292178765e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 26000/ 37905 | consumed samples: 6656000 | consumed tokens: 13631488000 | elapsed time per iteration (s): 0.21 | learning rate: 6.037E-05 | global batch size: 256 | lm loss: 2.936046E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.722 | TFLOPs: 7.92 | + 0: steps: 26000 loss: 2.9624 iter time (s): 0.218 samples/sec: 1176.327 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 26000 | lm loss value: 2.771734E+00 | lm loss PPL: 1.598633E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 26000 to checkpoints_83m + 0: [2022-11-24 15:45:25,890] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step26000 is begin to save! + 0: [2022-11-24 15:45:25,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:45:25,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:45:25,970] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:45:25,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:45:25,982] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:45:25,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:45:25,993] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,005] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,016] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,027] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,037] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,048] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,059] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,059] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,070] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,081] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,081] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:45:26,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:45:26,082] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step26000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:45:26,082] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:45:26,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:45:26,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:45:26,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +31: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:45:26,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 1: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 6: [2022-11-24 15:45:26,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +20: [2022-11-24 15:45:26,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:45:26,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,158] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,151] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step26000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:45:26,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:45:26,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +27: [2022-11-24 15:45:26,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:45:26,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:45:26,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:45:26,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +10: [2022-11-24 15:45:26,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +22: [2022-11-24 15:45:26,162] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:45:26,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:45:26,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +23: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,163] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:45:26,163] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:45:26,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 6: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:45:26,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:45:26,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +20: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 1: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,164] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:45:26,164] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:45:26,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:45:26,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 7: [2022-11-24 15:45:26,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,165] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:45:26,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:45:26,166] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:45:26,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +31: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:45:26,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:45:26,167] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +12: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +12: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +27: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:45:26,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +28: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,168] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:45:26,168] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +22: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +23: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,169] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:45:26,169] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:45:26,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +10: [2022-11-24 15:45:26,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +10: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:45:26,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 5: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:45:26,170] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 6: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:45:26,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +20: [2022-11-24 15:45:26,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +19: [2022-11-24 15:45:26,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,171] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 7: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +11: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,172] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,172] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +31: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:45:26,173] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:45:26,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +27: [2022-11-24 15:45:26,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:45:26,174] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:45:26,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,175] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:45:26,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +22: [2022-11-24 15:45:26,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:45:26,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,176] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +10: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +23: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 5: [2022-11-24 15:45:26,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:45:26,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +21: [2022-11-24 15:45:26,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:45:26,177] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 6: [2022-11-24 15:45:26,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:45:26,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +20: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 1: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,178] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:45:26,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:45:26,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:45:26,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +31: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,179] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +31: [2022-11-24 15:45:26,179] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:45:26,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,180] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:45:26,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:45:26,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +27: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:45:26,181] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,181] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +22: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,182] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:45:26,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:45:26,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 5: [2022-11-24 15:45:26,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:45:26,183] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,183] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +23: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +10: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:45:26,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,184] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:45:26,184] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 6: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +20: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 7: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:45:26,185] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 1: [2022-11-24 15:45:26,185] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +12: [2022-11-24 15:45:26,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +12: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +31: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:45:26,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,186] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:45:26,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,187] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:45:26,187] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:45:26,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +28: [2022-11-24 15:45:26,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +26: [2022-11-24 15:45:26,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +27: [2022-11-24 15:45:26,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:45:26,188] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:45:26,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +13: [2022-11-24 15:45:26,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +16: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:45:26,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +22: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,189] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:45:26,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +23: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 5: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:45:26,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +10: [2022-11-24 15:45:26,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 5: [2022-11-24 15:45:26,190] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,190] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:45:26,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:45:26,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +19: [2022-11-24 15:45:26,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +20: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 7: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,191] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 1: [2022-11-24 15:45:26,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:45:26,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:45:26,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:45:26,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:45:26,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,192] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:45:26,192] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:45:26,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +12: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +12: [2022-11-24 15:45:26,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +31: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +12: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:45:26,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +12: [2022-11-24 15:45:26,193] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:45:26,193] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:45:26,194] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:45:26,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +27: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:45:26,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:45:26,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +13: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +22: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,195] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:45:26,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:45:26,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +10: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,196] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:45:26,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +23: [2022-11-24 15:45:26,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:45:26,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 6: [2022-11-24 15:45:26,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:45:26,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:45:26,197] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,197] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:45:26,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 1: [2022-11-24 15:45:26,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +20: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 7: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:45:26,198] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:45:26,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +31: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,199] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: [2022-11-24 15:45:26,199] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:45:26,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +27: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:45:26,200] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:45:26,200] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +13: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,201] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:45:26,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:45:26,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,202] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:45:26,202] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +18: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +22: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +25: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 2: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +14: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +31: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +14: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 6: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +13: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +23: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +11: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +12: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +31: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +10: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 8: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 4: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +26: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +23: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +17: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +11: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +25: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +30: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +16: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +19: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +11: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +30: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +16: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 1: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +21: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +12: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +10: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +19: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 3: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +26: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +15: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 9: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +12: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 5: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +28: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +10: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +21: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +28: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +27: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +10: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +29: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +29: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 5: [2022-11-24 15:45:26,203] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:45:26,203] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! +24: [2022-11-24 15:45:26,204] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step26000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 15:45:26,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step26000 is ready now! + 0: successfully saved checkpoint at iteration 26000 to checkpoints_83m +31: time (ms) | save-checkpoint: 318.72 +31: iteration 26010/ 37905 | consumed samples: 6658560 | consumed tokens: 13636730880 | elapsed time per iteration (s): 0.25 | learning rate: 6.031E-05 | global batch size: 256 | lm loss: 2.894434E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.759 | TFLOPs: 6.55 | +31: iteration 26020/ 37905 | consumed samples: 6661120 | consumed tokens: 13641973760 | elapsed time per iteration (s): 0.22 | learning rate: 6.025E-05 | global batch size: 256 | lm loss: 2.912157E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.199 | TFLOPs: 7.31 | +31: iteration 26030/ 37905 | consumed samples: 6663680 | consumed tokens: 13647216640 | elapsed time per iteration (s): 0.20 | learning rate: 6.018E-05 | global batch size: 256 | lm loss: 2.945787E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.921 | TFLOPs: 8.25 | +31: iteration 26040/ 37905 | consumed samples: 6666240 | consumed tokens: 13652459520 | elapsed time per iteration (s): 0.22 | learning rate: 6.012E-05 | global batch size: 256 | lm loss: 2.897316E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.049 | TFLOPs: 7.34 | +31: iteration 26050/ 37905 | consumed samples: 6668800 | consumed tokens: 13657702400 | elapsed time per iteration (s): 0.23 | learning rate: 6.006E-05 | global batch size: 256 | lm loss: 2.914549E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.205 | TFLOPs: 7.22 | +31: iteration 26060/ 37905 | consumed samples: 6671360 | consumed tokens: 13662945280 | elapsed time per iteration (s): 0.20 | learning rate: 6.000E-05 | global batch size: 256 | lm loss: 2.952895E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.975 | TFLOPs: 8.22 | +31: iteration 26070/ 37905 | consumed samples: 6673920 | consumed tokens: 13668188160 | elapsed time per iteration (s): 0.26 | learning rate: 5.994E-05 | global batch size: 256 | lm loss: 2.906660E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 976.599 | TFLOPs: 6.22 | +31: iteration 26080/ 37905 | consumed samples: 6676480 | consumed tokens: 13673431040 | elapsed time per iteration (s): 0.21 | learning rate: 5.987E-05 | global batch size: 256 | lm loss: 2.916675E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.034 | TFLOPs: 7.64 | +31: iteration 26090/ 37905 | consumed samples: 6679040 | consumed tokens: 13678673920 | elapsed time per iteration (s): 0.21 | learning rate: 5.981E-05 | global batch size: 256 | lm loss: 2.895801E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.561 | TFLOPs: 7.91 | +31: iteration 26100/ 37905 | consumed samples: 6681600 | consumed tokens: 13683916800 | elapsed time per iteration (s): 0.23 | learning rate: 5.975E-05 | global batch size: 256 | lm loss: 2.920774E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.676 | TFLOPs: 7.11 | +31: iteration 26110/ 37905 | consumed samples: 6684160 | consumed tokens: 13689159680 | elapsed time per iteration (s): 0.20 | learning rate: 5.969E-05 | global batch size: 256 | lm loss: 2.926841E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.016 | TFLOPs: 7.99 | +31: iteration 26120/ 37905 | consumed samples: 6686720 | consumed tokens: 13694402560 | elapsed time per iteration (s): 0.24 | learning rate: 5.963E-05 | global batch size: 256 | lm loss: 2.914168E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.208 | TFLOPs: 6.75 | +31: iteration 26130/ 37905 | consumed samples: 6689280 | consumed tokens: 13699645440 | elapsed time per iteration (s): 0.22 | learning rate: 5.956E-05 | global batch size: 256 | lm loss: 2.911136E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.104 | TFLOPs: 7.58 | +31: iteration 26140/ 37905 | consumed samples: 6691840 | consumed tokens: 13704888320 | elapsed time per iteration (s): 0.21 | learning rate: 5.950E-05 | global batch size: 256 | lm loss: 2.903558E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.582 | TFLOPs: 7.92 | +31: iteration 26150/ 37905 | consumed samples: 6694400 | consumed tokens: 13710131200 | elapsed time per iteration (s): 0.20 | learning rate: 5.944E-05 | global batch size: 256 | lm loss: 2.893738E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.489 | TFLOPs: 8.26 | +31: iteration 26160/ 37905 | consumed samples: 6696960 | consumed tokens: 13715374080 | elapsed time per iteration (s): 0.21 | learning rate: 5.938E-05 | global batch size: 256 | lm loss: 2.872993E+00 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.009 | TFLOPs: 7.80 | +31: iteration 26170/ 37905 | consumed samples: 6699520 | consumed tokens: 13720616960 | elapsed time per iteration (s): 0.24 | learning rate: 5.932E-05 | global batch size: 256 | lm loss: 2.902997E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.394 | TFLOPs: 6.69 | +31: iteration 26180/ 37905 | consumed samples: 6702080 | consumed tokens: 13725859840 | elapsed time per iteration (s): 0.23 | learning rate: 5.926E-05 | global batch size: 256 | lm loss: 2.903873E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.302 | TFLOPs: 6.95 | +31: iteration 26190/ 37905 | consumed samples: 6704640 | consumed tokens: 13731102720 | elapsed time per iteration (s): 0.23 | learning rate: 5.919E-05 | global batch size: 256 | lm loss: 2.908706E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.775 | TFLOPs: 7.12 | +31: iteration 26200/ 37905 | consumed samples: 6707200 | consumed tokens: 13736345600 | elapsed time per iteration (s): 0.21 | learning rate: 5.913E-05 | global batch size: 256 | lm loss: 2.924036E+00 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1198.338 | TFLOPs: 7.63 | +31: iteration 26210/ 37905 | consumed samples: 6709760 | consumed tokens: 13741588480 | elapsed time per iteration (s): 0.22 | learning rate: 5.907E-05 | global batch size: 256 | lm loss: 2.923652E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.290 | TFLOPs: 7.40 | +31: iteration 26220/ 37905 | consumed samples: 6712320 | consumed tokens: 13746831360 | elapsed time per iteration (s): 0.25 | learning rate: 5.901E-05 | global batch size: 256 | lm loss: 2.942247E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.484 | TFLOPs: 6.62 | +31: iteration 26230/ 37905 | consumed samples: 6714880 | consumed tokens: 13752074240 | elapsed time per iteration (s): 0.25 | learning rate: 5.895E-05 | global batch size: 256 | lm loss: 2.902270E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.627 | TFLOPs: 6.63 | +31: iteration 26240/ 37905 | consumed samples: 6717440 | consumed tokens: 13757317120 | elapsed time per iteration (s): 0.23 | learning rate: 5.889E-05 | global batch size: 256 | lm loss: 2.899878E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.313 | TFLOPs: 7.23 | +31: iteration 26250/ 37905 | consumed samples: 6720000 | consumed tokens: 13762560000 | elapsed time per iteration (s): 0.21 | learning rate: 5.882E-05 | global batch size: 256 | lm loss: 2.900881E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.525 | TFLOPs: 7.79 | +31: iteration 26260/ 37905 | consumed samples: 6722560 | consumed tokens: 13767802880 | elapsed time per iteration (s): 0.22 | learning rate: 5.876E-05 | global batch size: 256 | lm loss: 2.898704E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.175 | TFLOPs: 7.31 | +31: iteration 26270/ 37905 | consumed samples: 6725120 | consumed tokens: 13773045760 | elapsed time per iteration (s): 0.22 | learning rate: 5.870E-05 | global batch size: 256 | lm loss: 2.897035E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.328 | TFLOPs: 7.43 | +31: iteration 26280/ 37905 | consumed samples: 6727680 | consumed tokens: 13778288640 | elapsed time per iteration (s): 0.34 | learning rate: 5.864E-05 | global batch size: 256 | lm loss: 2.909970E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 760.923 | TFLOPs: 4.85 | +31: iteration 26290/ 37905 | consumed samples: 6730240 | consumed tokens: 13783531520 | elapsed time per iteration (s): 0.20 | learning rate: 5.858E-05 | global batch size: 256 | lm loss: 2.931398E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.352 | TFLOPs: 8.14 | +31: iteration 26300/ 37905 | consumed samples: 6732800 | consumed tokens: 13788774400 | elapsed time per iteration (s): 0.21 | learning rate: 5.852E-05 | global batch size: 256 | lm loss: 2.910895E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.954 | TFLOPs: 7.66 | +31: iteration 26310/ 37905 | consumed samples: 6735360 | consumed tokens: 13794017280 | elapsed time per iteration (s): 0.20 | learning rate: 5.846E-05 | global batch size: 256 | lm loss: 2.918111E+00 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.445 | TFLOPs: 8.21 | +31: iteration 26320/ 37905 | consumed samples: 6737920 | consumed tokens: 13799260160 | elapsed time per iteration (s): 0.20 | learning rate: 5.840E-05 | global batch size: 256 | lm loss: 2.919323E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1261.766 | TFLOPs: 8.04 | +31: iteration 26330/ 37905 | consumed samples: 6740480 | consumed tokens: 13804503040 | elapsed time per iteration (s): 0.19 | learning rate: 5.834E-05 | global batch size: 256 | lm loss: 2.952957E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.712 | TFLOPs: 8.43 | +31: iteration 26340/ 37905 | consumed samples: 6743040 | consumed tokens: 13809745920 | elapsed time per iteration (s): 0.19 | learning rate: 5.827E-05 | global batch size: 256 | lm loss: 2.935118E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.304 | TFLOPs: 8.36 | +31: iteration 26350/ 37905 | consumed samples: 6745600 | consumed tokens: 13814988800 | elapsed time per iteration (s): 0.20 | learning rate: 5.821E-05 | global batch size: 256 | lm loss: 2.913908E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.342 | TFLOPs: 8.21 | +31: iteration 26360/ 37905 | consumed samples: 6748160 | consumed tokens: 13820231680 | elapsed time per iteration (s): 0.23 | learning rate: 5.815E-05 | global batch size: 256 | lm loss: 2.871634E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.026 | TFLOPs: 6.94 | +31: iteration 26370/ 37905 | consumed samples: 6750720 | consumed tokens: 13825474560 | elapsed time per iteration (s): 0.22 | learning rate: 5.809E-05 | global batch size: 256 | lm loss: 2.922728E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.551 | TFLOPs: 7.30 | +31: iteration 26380/ 37905 | consumed samples: 6753280 | consumed tokens: 13830717440 | elapsed time per iteration (s): 0.20 | learning rate: 5.803E-05 | global batch size: 256 | lm loss: 2.929114E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1286.518 | TFLOPs: 8.19 | +31: iteration 26390/ 37905 | consumed samples: 6755840 | consumed tokens: 13835960320 | elapsed time per iteration (s): 0.20 | learning rate: 5.797E-05 | global batch size: 256 | lm loss: 2.942346E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.023 | TFLOPs: 8.06 | +31: iteration 26400/ 37905 | consumed samples: 6758400 | consumed tokens: 13841203200 | elapsed time per iteration (s): 0.19 | learning rate: 5.791E-05 | global batch size: 256 | lm loss: 2.899630E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.749 | TFLOPs: 8.38 | +31: iteration 26410/ 37905 | consumed samples: 6760960 | consumed tokens: 13846446080 | elapsed time per iteration (s): 0.22 | learning rate: 5.785E-05 | global batch size: 256 | lm loss: 2.938484E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.917 | TFLOPs: 7.29 | +31: iteration 26420/ 37905 | consumed samples: 6763520 | consumed tokens: 13851688960 | elapsed time per iteration (s): 0.23 | learning rate: 5.779E-05 | global batch size: 256 | lm loss: 2.896140E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.947 | TFLOPs: 7.22 | +31: iteration 26430/ 37905 | consumed samples: 6766080 | consumed tokens: 13856931840 | elapsed time per iteration (s): 0.21 | learning rate: 5.773E-05 | global batch size: 256 | lm loss: 2.859535E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.883 | TFLOPs: 7.90 | +31: iteration 26440/ 37905 | consumed samples: 6768640 | consumed tokens: 13862174720 | elapsed time per iteration (s): 0.24 | learning rate: 5.767E-05 | global batch size: 256 | lm loss: 2.976700E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.457 | TFLOPs: 6.93 | +31: iteration 26450/ 37905 | consumed samples: 6771200 | consumed tokens: 13867417600 | elapsed time per iteration (s): 0.21 | learning rate: 5.760E-05 | global batch size: 256 | lm loss: 2.901343E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.610 | TFLOPs: 7.94 | +31: iteration 26460/ 37905 | consumed samples: 6773760 | consumed tokens: 13872660480 | elapsed time per iteration (s): 0.22 | learning rate: 5.754E-05 | global batch size: 256 | lm loss: 2.914291E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.993 | TFLOPs: 7.43 | +31: iteration 26470/ 37905 | consumed samples: 6776320 | consumed tokens: 13877903360 | elapsed time per iteration (s): 0.22 | learning rate: 5.748E-05 | global batch size: 256 | lm loss: 2.900445E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.203 | TFLOPs: 7.54 | +31: iteration 26480/ 37905 | consumed samples: 6778880 | consumed tokens: 13883146240 | elapsed time per iteration (s): 0.23 | learning rate: 5.742E-05 | global batch size: 256 | lm loss: 2.900441E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.780 | TFLOPs: 7.11 | +31: iteration 26490/ 37905 | consumed samples: 6781440 | consumed tokens: 13888389120 | elapsed time per iteration (s): 0.21 | learning rate: 5.736E-05 | global batch size: 256 | lm loss: 2.893346E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.193 | TFLOPs: 7.80 | +31: iteration 26500/ 37905 | consumed samples: 6784000 | consumed tokens: 13893632000 | elapsed time per iteration (s): 0.22 | learning rate: 5.730E-05 | global batch size: 256 | lm loss: 2.916034E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.800 | TFLOPs: 7.28 | +31: iteration 26510/ 37905 | consumed samples: 6786560 | consumed tokens: 13898874880 | elapsed time per iteration (s): 0.21 | learning rate: 5.724E-05 | global batch size: 256 | lm loss: 2.922230E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.421 | TFLOPs: 7.72 | +31: iteration 26520/ 37905 | consumed samples: 6789120 | consumed tokens: 13904117760 | elapsed time per iteration (s): 0.22 | learning rate: 5.718E-05 | global batch size: 256 | lm loss: 2.917542E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.295 | TFLOPs: 7.42 | +31: iteration 26530/ 37905 | consumed samples: 6791680 | consumed tokens: 13909360640 | elapsed time per iteration (s): 0.23 | learning rate: 5.712E-05 | global batch size: 256 | lm loss: 2.916507E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.455 | TFLOPs: 7.16 | +31: iteration 26540/ 37905 | consumed samples: 6794240 | consumed tokens: 13914603520 | elapsed time per iteration (s): 0.22 | learning rate: 5.706E-05 | global batch size: 256 | lm loss: 2.891981E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.822 | TFLOPs: 7.54 | +31: iteration 26550/ 37905 | consumed samples: 6796800 | consumed tokens: 13919846400 | elapsed time per iteration (s): 0.22 | learning rate: 5.700E-05 | global batch size: 256 | lm loss: 2.935114E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.257 | TFLOPs: 7.39 | +31: iteration 26560/ 37905 | consumed samples: 6799360 | consumed tokens: 13925089280 | elapsed time per iteration (s): 0.23 | learning rate: 5.694E-05 | global batch size: 256 | lm loss: 2.911646E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.359 | TFLOPs: 7.21 | +31: iteration 26570/ 37905 | consumed samples: 6801920 | consumed tokens: 13930332160 | elapsed time per iteration (s): 0.22 | learning rate: 5.688E-05 | global batch size: 256 | lm loss: 2.874707E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.584 | TFLOPs: 7.28 | +31: iteration 26580/ 37905 | consumed samples: 6804480 | consumed tokens: 13935575040 | elapsed time per iteration (s): 0.20 | learning rate: 5.682E-05 | global batch size: 256 | lm loss: 2.921904E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.624 | TFLOPs: 7.96 | +31: iteration 26590/ 37905 | consumed samples: 6807040 | consumed tokens: 13940817920 | elapsed time per iteration (s): 0.21 | learning rate: 5.676E-05 | global batch size: 256 | lm loss: 2.891911E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.333 | TFLOPs: 7.68 | +31: iteration 26600/ 37905 | consumed samples: 6809600 | consumed tokens: 13946060800 | elapsed time per iteration (s): 0.20 | learning rate: 5.670E-05 | global batch size: 256 | lm loss: 2.912693E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1260.592 | TFLOPs: 8.03 | +31: iteration 26610/ 37905 | consumed samples: 6812160 | consumed tokens: 13951303680 | elapsed time per iteration (s): 0.22 | learning rate: 5.664E-05 | global batch size: 256 | lm loss: 2.908920E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.732 | TFLOPs: 7.53 | +31: iteration 26620/ 37905 | consumed samples: 6814720 | consumed tokens: 13956546560 | elapsed time per iteration (s): 0.22 | learning rate: 5.658E-05 | global batch size: 256 | lm loss: 2.915981E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1188.032 | TFLOPs: 7.57 | +31: iteration 26630/ 37905 | consumed samples: 6817280 | consumed tokens: 13961789440 | elapsed time per iteration (s): 0.22 | learning rate: 5.652E-05 | global batch size: 256 | lm loss: 2.911612E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.501 | TFLOPs: 7.28 | +31: iteration 26640/ 37905 | consumed samples: 6819840 | consumed tokens: 13967032320 | elapsed time per iteration (s): 0.22 | learning rate: 5.646E-05 | global batch size: 256 | lm loss: 2.924307E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1180.874 | TFLOPs: 7.52 | +31: iteration 26650/ 37905 | consumed samples: 6822400 | consumed tokens: 13972275200 | elapsed time per iteration (s): 0.23 | learning rate: 5.640E-05 | global batch size: 256 | lm loss: 2.902408E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.245 | TFLOPs: 7.23 | +31: iteration 26660/ 37905 | consumed samples: 6824960 | consumed tokens: 13977518080 | elapsed time per iteration (s): 0.23 | learning rate: 5.634E-05 | global batch size: 256 | lm loss: 2.888653E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.930 | TFLOPs: 7.04 | +31: iteration 26670/ 37905 | consumed samples: 6827520 | consumed tokens: 13982760960 | elapsed time per iteration (s): 0.26 | learning rate: 5.628E-05 | global batch size: 256 | lm loss: 2.933181E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 984.503 | TFLOPs: 6.27 | +31: iteration 26680/ 37905 | consumed samples: 6830080 | consumed tokens: 13988003840 | elapsed time per iteration (s): 0.30 | learning rate: 5.622E-05 | global batch size: 256 | lm loss: 2.948084E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 860.582 | TFLOPs: 5.48 | +31: iteration 26690/ 37905 | consumed samples: 6832640 | consumed tokens: 13993246720 | elapsed time per iteration (s): 0.22 | learning rate: 5.616E-05 | global batch size: 256 | lm loss: 2.886172E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.210 | TFLOPs: 7.51 | +31: iteration 26700/ 37905 | consumed samples: 6835200 | consumed tokens: 13998489600 | elapsed time per iteration (s): 0.23 | learning rate: 5.610E-05 | global batch size: 256 | lm loss: 2.926399E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.442 | TFLOPs: 7.22 | +31: iteration 26710/ 37905 | consumed samples: 6837760 | consumed tokens: 14003732480 | elapsed time per iteration (s): 0.24 | learning rate: 5.604E-05 | global batch size: 256 | lm loss: 2.895160E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.651 | TFLOPs: 6.76 | +31: iteration 26720/ 37905 | consumed samples: 6840320 | consumed tokens: 14008975360 | elapsed time per iteration (s): 0.21 | learning rate: 5.598E-05 | global batch size: 256 | lm loss: 2.924069E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.752 | TFLOPs: 7.69 | +31: iteration 26730/ 37905 | consumed samples: 6842880 | consumed tokens: 14014218240 | elapsed time per iteration (s): 0.22 | learning rate: 5.592E-05 | global batch size: 256 | lm loss: 2.911062E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.326 | TFLOPs: 7.52 | +31: iteration 26740/ 37905 | consumed samples: 6845440 | consumed tokens: 14019461120 | elapsed time per iteration (s): 0.24 | learning rate: 5.586E-05 | global batch size: 256 | lm loss: 2.900940E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.241 | TFLOPs: 6.80 | +31: iteration 26750/ 37905 | consumed samples: 6848000 | consumed tokens: 14024704000 | elapsed time per iteration (s): 0.20 | learning rate: 5.580E-05 | global batch size: 256 | lm loss: 2.921782E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.509 | TFLOPs: 7.99 | +31: iteration 26760/ 37905 | consumed samples: 6850560 | consumed tokens: 14029946880 | elapsed time per iteration (s): 0.24 | learning rate: 5.574E-05 | global batch size: 256 | lm loss: 2.901794E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.273 | TFLOPs: 6.80 | +31: iteration 26770/ 37905 | consumed samples: 6853120 | consumed tokens: 14035189760 | elapsed time per iteration (s): 0.21 | learning rate: 5.568E-05 | global batch size: 256 | lm loss: 2.932346E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.587 | TFLOPs: 7.59 | +31: iteration 26780/ 37905 | consumed samples: 6855680 | consumed tokens: 14040432640 | elapsed time per iteration (s): 0.25 | learning rate: 5.562E-05 | global batch size: 256 | lm loss: 2.923188E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.345 | TFLOPs: 6.61 | +31: iteration 26790/ 37905 | consumed samples: 6858240 | consumed tokens: 14045675520 | elapsed time per iteration (s): 0.21 | learning rate: 5.556E-05 | global batch size: 256 | lm loss: 2.884191E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.533 | TFLOPs: 7.62 | +31: iteration 26800/ 37905 | consumed samples: 6860800 | consumed tokens: 14050918400 | elapsed time per iteration (s): 0.21 | learning rate: 5.550E-05 | global batch size: 256 | lm loss: 2.911842E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.134 | TFLOPs: 7.83 | +31: iteration 26810/ 37905 | consumed samples: 6863360 | consumed tokens: 14056161280 | elapsed time per iteration (s): 0.23 | learning rate: 5.545E-05 | global batch size: 256 | lm loss: 2.881179E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.965 | TFLOPs: 7.10 | +31: iteration 26820/ 37905 | consumed samples: 6865920 | consumed tokens: 14061404160 | elapsed time per iteration (s): 0.23 | learning rate: 5.539E-05 | global batch size: 256 | lm loss: 2.903571E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.938 | TFLOPs: 7.18 | +31: iteration 26830/ 37905 | consumed samples: 6868480 | consumed tokens: 14066647040 | elapsed time per iteration (s): 0.23 | learning rate: 5.533E-05 | global batch size: 256 | lm loss: 2.870089E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.101 | TFLOPs: 6.99 | +31: iteration 26840/ 37905 | consumed samples: 6871040 | consumed tokens: 14071889920 | elapsed time per iteration (s): 0.25 | learning rate: 5.527E-05 | global batch size: 256 | lm loss: 2.897655E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.560 | TFLOPs: 6.50 | +31: iteration 26850/ 37905 | consumed samples: 6873600 | consumed tokens: 14077132800 | elapsed time per iteration (s): 0.23 | learning rate: 5.521E-05 | global batch size: 256 | lm loss: 2.914437E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.011 | TFLOPs: 7.01 | +31: iteration 26860/ 37905 | consumed samples: 6876160 | consumed tokens: 14082375680 | elapsed time per iteration (s): 0.26 | learning rate: 5.515E-05 | global batch size: 256 | lm loss: 2.897070E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.491 | TFLOPs: 6.35 | +31: iteration 26870/ 37905 | consumed samples: 6878720 | consumed tokens: 14087618560 | elapsed time per iteration (s): 0.25 | learning rate: 5.509E-05 | global batch size: 256 | lm loss: 2.905796E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.590 | TFLOPs: 6.65 | +31: iteration 26880/ 37905 | consumed samples: 6881280 | consumed tokens: 14092861440 | elapsed time per iteration (s): 0.21 | learning rate: 5.503E-05 | global batch size: 256 | lm loss: 2.903787E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.836 | TFLOPs: 7.71 | +31: iteration 26890/ 37905 | consumed samples: 6883840 | consumed tokens: 14098104320 | elapsed time per iteration (s): 0.22 | learning rate: 5.497E-05 | global batch size: 256 | lm loss: 2.894035E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.506 | TFLOPs: 7.25 | +31: iteration 26900/ 37905 | consumed samples: 6886400 | consumed tokens: 14103347200 | elapsed time per iteration (s): 0.24 | learning rate: 5.491E-05 | global batch size: 256 | lm loss: 2.927956E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.185 | TFLOPs: 6.85 | +31: iteration 26910/ 37905 | consumed samples: 6888960 | consumed tokens: 14108590080 | elapsed time per iteration (s): 0.22 | learning rate: 5.485E-05 | global batch size: 256 | lm loss: 2.875821E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.702 | TFLOPs: 7.51 | +31: iteration 26920/ 37905 | consumed samples: 6891520 | consumed tokens: 14113832960 | elapsed time per iteration (s): 0.22 | learning rate: 5.479E-05 | global batch size: 256 | lm loss: 2.913457E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.623 | TFLOPs: 7.44 | +31: iteration 26930/ 37905 | consumed samples: 6894080 | consumed tokens: 14119075840 | elapsed time per iteration (s): 0.22 | learning rate: 5.474E-05 | global batch size: 256 | lm loss: 2.919539E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.308 | TFLOPs: 7.33 | +31: iteration 26940/ 37905 | consumed samples: 6896640 | consumed tokens: 14124318720 | elapsed time per iteration (s): 0.23 | learning rate: 5.468E-05 | global batch size: 256 | lm loss: 2.904389E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.890 | TFLOPs: 7.12 | +31: iteration 26950/ 37905 | consumed samples: 6899200 | consumed tokens: 14129561600 | elapsed time per iteration (s): 0.21 | learning rate: 5.462E-05 | global batch size: 256 | lm loss: 2.909039E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.457 | TFLOPs: 7.67 | +31: iteration 26960/ 37905 | consumed samples: 6901760 | consumed tokens: 14134804480 | elapsed time per iteration (s): 0.22 | learning rate: 5.456E-05 | global batch size: 256 | lm loss: 2.899270E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.785 | TFLOPs: 7.48 | +31: iteration 26970/ 37905 | consumed samples: 6904320 | consumed tokens: 14140047360 | elapsed time per iteration (s): 0.21 | learning rate: 5.450E-05 | global batch size: 256 | lm loss: 2.886911E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.681 | TFLOPs: 7.81 | +31: iteration 26980/ 37905 | consumed samples: 6906880 | consumed tokens: 14145290240 | elapsed time per iteration (s): 0.22 | learning rate: 5.444E-05 | global batch size: 256 | lm loss: 2.911609E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.432 | TFLOPs: 7.27 | +31: iteration 26990/ 37905 | consumed samples: 6909440 | consumed tokens: 14150533120 | elapsed time per iteration (s): 0.22 | learning rate: 5.438E-05 | global batch size: 256 | lm loss: 2.931480E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.083 | TFLOPs: 7.28 | +31: iteration 27000/ 37905 | consumed samples: 6912000 | consumed tokens: 14155776000 | elapsed time per iteration (s): 0.24 | learning rate: 5.432E-05 | global batch size: 256 | lm loss: 2.911845E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.738 | TFLOPs: 6.85 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 27000 | lm loss value: 2.832203E+00 | lm loss PPL: 1.698283E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 27000 to checkpoints_83m + 0: [2022-11-24 15:49:08,831] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step27000 is begin to save! + 0: [2022-11-24 15:49:08,842] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,926] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,937] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,948] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,959] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,970] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,981] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:49:08,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:49:08,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:49:09,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:49:09,003] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:49:09,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:49:09,014] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:49:09,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:49:09,025] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:49:09,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:49:09,026] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step27000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:49:09,026] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:49:09,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step27000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +15: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,101] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:49:09,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 8: [2022-11-24 15:49:09,102] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,102] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,102] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:49:09,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +10: [2022-11-24 15:49:09,103] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,103] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,103] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:49:09,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +23: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +12: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +20: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,104] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:49:09,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +31: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:49:09,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,105] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +27: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +17: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +29: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,106] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:49:09,106] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:49:09,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +11: [2022-11-24 15:49:09,107] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,107] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,107] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +10: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,108] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +12: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,108] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,108] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +15: [2022-11-24 15:49:09,108] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +12: [2022-11-24 15:49:09,108] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 9: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 9: [2022-11-24 15:49:09,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:49:09,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,109] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 15:49:09,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 8: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:49:09,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +23: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 3: [2022-11-24 15:49:09,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +20: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +22: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,110] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 15:49:09,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:49:09,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,111] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,111] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,111] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +28: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +31: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,112] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +17: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:49:09,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +19: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,113] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +11: [2022-11-24 15:49:09,113] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:49:09,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,114] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:49:09,114] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +10: [2022-11-24 15:49:09,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 15:49:09,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +12: [2022-11-24 15:49:09,115] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,115] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:49:09,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +23: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:49:09,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 8: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 3: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,116] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:49:09,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +20: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:49:09,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,117] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,117] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:49:09,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +31: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,118] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 15:49:09,118] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:49:09,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:49:09,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +30: [2022-11-24 15:49:09,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +17: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +29: [2022-11-24 15:49:09,119] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,119] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +19: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:49:09,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +11: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,120] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:49:09,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 9: [2022-11-24 15:49:09,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:49:09,121] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,121] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +10: [2022-11-24 15:49:09,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +12: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:49:09,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,122] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:49:09,122] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +23: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 8: [2022-11-24 15:49:09,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:49:09,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,123] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 3: [2022-11-24 15:49:09,123] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:49:09,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:49:09,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +20: [2022-11-24 15:49:09,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,124] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,124] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,125] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:49:09,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,125] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +27: [2022-11-24 15:49:09,125] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,125] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,125] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +31: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +31: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +30: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,126] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,126] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +17: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +19: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,127] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:49:09,127] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:49:09,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +11: [2022-11-24 15:49:09,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,128] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,128] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:49:09,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 9: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +12: [2022-11-24 15:49:09,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,129] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:49:09,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 8: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:49:09,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,130] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 15:49:09,130] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 3: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +23: [2022-11-24 15:49:09,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:49:09,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +20: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,131] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:49:09,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:49:09,132] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:49:09,132] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:49:09,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +31: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,133] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:49:09,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +30: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:49:09,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,134] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:49:09,134] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +17: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +19: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,135] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:49:09,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +10: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 9: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,136] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:49:09,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 15:49:09,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +12: [2022-11-24 15:49:09,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,137] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,137] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:49:09,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +16: [2022-11-24 15:49:09,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 8: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:49:09,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +23: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 3: [2022-11-24 15:49:09,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,138] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:49:09,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +20: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:49:09,139] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:49:09,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:49:09,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:49:09,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:49:09,140] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:49:09,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +31: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +30: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:49:09,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +30: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,141] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:49:09,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +19: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +17: [2022-11-24 15:49:09,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,142] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:49:09,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:49:09,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,143] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +10: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +15: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +18: [2022-11-24 15:49:09,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,144] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +12: [2022-11-24 15:49:09,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 8: [2022-11-24 15:49:09,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +25: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +23: [2022-11-24 15:49:09,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,145] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,145] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:49:09,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 3: [2022-11-24 15:49:09,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +20: [2022-11-24 15:49:09,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,146] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +31: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +28: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +22: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +20: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +29: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +30: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +26: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +18: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +17: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +29: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +25: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +26: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +15: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +17: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 9: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +22: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 2: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +13: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +15: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 7: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +23: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +11: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +31: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,147] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +10: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,147] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 3: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +13: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +18: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +11: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +10: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +22: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +14: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 6: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 9: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +31: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +28: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +27: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +24: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +11: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 5: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +28: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +27: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +14: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +24: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +11: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +19: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 4: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +16: [2022-11-24 15:49:09,148] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:49:09,148] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! +21: [2022-11-24 15:49:09,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:49:09,150] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:49:09,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,159] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,160] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,161] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,161] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:49:09,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,161] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step27000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:49:09,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 1: [2022-11-24 15:49:09,162] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step27000 is ready now! + 0: successfully saved checkpoint at iteration 27000 to checkpoints_83m +31: time (ms) | save-checkpoint: 349.70 +31: iteration 27010/ 37905 | consumed samples: 6914560 | consumed tokens: 14161018880 | elapsed time per iteration (s): 0.26 | learning rate: 5.427E-05 | global batch size: 256 | lm loss: 2.916598E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.738 | TFLOPs: 6.37 | +31: iteration 27020/ 37905 | consumed samples: 6917120 | consumed tokens: 14166261760 | elapsed time per iteration (s): 0.21 | learning rate: 5.421E-05 | global batch size: 256 | lm loss: 2.881158E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.896 | TFLOPs: 7.59 | +31: iteration 27030/ 37905 | consumed samples: 6919680 | consumed tokens: 14171504640 | elapsed time per iteration (s): 0.26 | learning rate: 5.415E-05 | global batch size: 256 | lm loss: 2.885146E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.023 | TFLOPs: 6.28 | +31: iteration 27040/ 37905 | consumed samples: 6922240 | consumed tokens: 14176747520 | elapsed time per iteration (s): 0.22 | learning rate: 5.409E-05 | global batch size: 256 | lm loss: 2.890314E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.489 | TFLOPs: 7.53 | +31: iteration 27050/ 37905 | consumed samples: 6924800 | consumed tokens: 14181990400 | elapsed time per iteration (s): 0.20 | learning rate: 5.403E-05 | global batch size: 256 | lm loss: 2.949781E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.175 | TFLOPs: 8.24 | +31: iteration 27060/ 37905 | consumed samples: 6927360 | consumed tokens: 14187233280 | elapsed time per iteration (s): 0.24 | learning rate: 5.397E-05 | global batch size: 256 | lm loss: 2.927624E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.309 | TFLOPs: 6.91 | +31: iteration 27070/ 37905 | consumed samples: 6929920 | consumed tokens: 14192476160 | elapsed time per iteration (s): 0.25 | learning rate: 5.392E-05 | global batch size: 256 | lm loss: 2.907086E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.317 | TFLOPs: 6.62 | +31: iteration 27080/ 37905 | consumed samples: 6932480 | consumed tokens: 14197719040 | elapsed time per iteration (s): 0.26 | learning rate: 5.386E-05 | global batch size: 256 | lm loss: 2.895040E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 977.780 | TFLOPs: 6.23 | +31: iteration 27090/ 37905 | consumed samples: 6935040 | consumed tokens: 14202961920 | elapsed time per iteration (s): 0.25 | learning rate: 5.380E-05 | global batch size: 256 | lm loss: 2.913299E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.833 | TFLOPs: 6.58 | +31: iteration 27100/ 37905 | consumed samples: 6937600 | consumed tokens: 14208204800 | elapsed time per iteration (s): 0.25 | learning rate: 5.374E-05 | global batch size: 256 | lm loss: 2.893850E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.976 | TFLOPs: 6.59 | +31: iteration 27110/ 37905 | consumed samples: 6940160 | consumed tokens: 14213447680 | elapsed time per iteration (s): 0.21 | learning rate: 5.368E-05 | global batch size: 256 | lm loss: 2.930707E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.400 | TFLOPs: 7.66 | +31: iteration 27120/ 37905 | consumed samples: 6942720 | consumed tokens: 14218690560 | elapsed time per iteration (s): 0.25 | learning rate: 5.362E-05 | global batch size: 256 | lm loss: 2.895399E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1041.532 | TFLOPs: 6.63 | +31: iteration 27130/ 37905 | consumed samples: 6945280 | consumed tokens: 14223933440 | elapsed time per iteration (s): 0.24 | learning rate: 5.357E-05 | global batch size: 256 | lm loss: 2.924702E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.929 | TFLOPs: 6.66 | +31: iteration 27140/ 37905 | consumed samples: 6947840 | consumed tokens: 14229176320 | elapsed time per iteration (s): 0.20 | learning rate: 5.351E-05 | global batch size: 256 | lm loss: 2.873667E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.341 | TFLOPs: 7.96 | +31: iteration 27150/ 37905 | consumed samples: 6950400 | consumed tokens: 14234419200 | elapsed time per iteration (s): 0.23 | learning rate: 5.345E-05 | global batch size: 256 | lm loss: 2.899731E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.859 | TFLOPs: 7.17 | +31: iteration 27160/ 37905 | consumed samples: 6952960 | consumed tokens: 14239662080 | elapsed time per iteration (s): 0.23 | learning rate: 5.339E-05 | global batch size: 256 | lm loss: 2.932401E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.990 | TFLOPs: 7.15 | +31: iteration 27170/ 37905 | consumed samples: 6955520 | consumed tokens: 14244904960 | elapsed time per iteration (s): 0.20 | learning rate: 5.333E-05 | global batch size: 256 | lm loss: 2.902516E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.571 | TFLOPs: 7.96 | +31: iteration 27180/ 37905 | consumed samples: 6958080 | consumed tokens: 14250147840 | elapsed time per iteration (s): 0.21 | learning rate: 5.328E-05 | global batch size: 256 | lm loss: 2.901574E+00 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.857 | TFLOPs: 7.74 | +31: iteration 27190/ 37905 | consumed samples: 6960640 | consumed tokens: 14255390720 | elapsed time per iteration (s): 0.23 | learning rate: 5.322E-05 | global batch size: 256 | lm loss: 2.920660E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.637 | TFLOPs: 7.02 | +31: iteration 27200/ 37905 | consumed samples: 6963200 | consumed tokens: 14260633600 | elapsed time per iteration (s): 0.22 | learning rate: 5.316E-05 | global batch size: 256 | lm loss: 2.913830E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.348 | TFLOPs: 7.49 | +31: iteration 27210/ 37905 | consumed samples: 6965760 | consumed tokens: 14265876480 | elapsed time per iteration (s): 0.21 | learning rate: 5.310E-05 | global batch size: 256 | lm loss: 2.912125E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.278 | TFLOPs: 7.75 | +31: iteration 27220/ 37905 | consumed samples: 6968320 | consumed tokens: 14271119360 | elapsed time per iteration (s): 0.20 | learning rate: 5.304E-05 | global batch size: 256 | lm loss: 2.909882E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1270.486 | TFLOPs: 8.09 | +31: iteration 27230/ 37905 | consumed samples: 6970880 | consumed tokens: 14276362240 | elapsed time per iteration (s): 0.22 | learning rate: 5.299E-05 | global batch size: 256 | lm loss: 2.912917E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.939 | TFLOPs: 7.29 | +31: iteration 27240/ 37905 | consumed samples: 6973440 | consumed tokens: 14281605120 | elapsed time per iteration (s): 0.21 | learning rate: 5.293E-05 | global batch size: 256 | lm loss: 2.880662E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.885 | TFLOPs: 7.69 | +31: iteration 27250/ 37905 | consumed samples: 6976000 | consumed tokens: 14286848000 | elapsed time per iteration (s): 0.29 | learning rate: 5.287E-05 | global batch size: 256 | lm loss: 2.906573E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 868.335 | TFLOPs: 5.53 | +31: iteration 27260/ 37905 | consumed samples: 6978560 | consumed tokens: 14292090880 | elapsed time per iteration (s): 0.26 | learning rate: 5.281E-05 | global batch size: 256 | lm loss: 2.893672E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 981.673 | TFLOPs: 6.25 | +31: iteration 27270/ 37905 | consumed samples: 6981120 | consumed tokens: 14297333760 | elapsed time per iteration (s): 0.22 | learning rate: 5.276E-05 | global batch size: 256 | lm loss: 2.883903E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.385 | TFLOPs: 7.54 | +31: iteration 27280/ 37905 | consumed samples: 6983680 | consumed tokens: 14302576640 | elapsed time per iteration (s): 0.26 | learning rate: 5.270E-05 | global batch size: 256 | lm loss: 2.910174E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.386 | TFLOPs: 6.33 | +31: iteration 27290/ 37905 | consumed samples: 6986240 | consumed tokens: 14307819520 | elapsed time per iteration (s): 0.23 | learning rate: 5.264E-05 | global batch size: 256 | lm loss: 2.915264E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.452 | TFLOPs: 7.07 | +31: iteration 27300/ 37905 | consumed samples: 6988800 | consumed tokens: 14313062400 | elapsed time per iteration (s): 0.22 | learning rate: 5.258E-05 | global batch size: 256 | lm loss: 2.917905E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.038 | TFLOPs: 7.58 | +31: iteration 27310/ 37905 | consumed samples: 6991360 | consumed tokens: 14318305280 | elapsed time per iteration (s): 0.23 | learning rate: 5.253E-05 | global batch size: 256 | lm loss: 2.919385E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.186 | TFLOPs: 6.94 | +31: iteration 27320/ 37905 | consumed samples: 6993920 | consumed tokens: 14323548160 | elapsed time per iteration (s): 0.24 | learning rate: 5.247E-05 | global batch size: 256 | lm loss: 2.918162E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.963 | TFLOPs: 6.66 | +31: iteration 27330/ 37905 | consumed samples: 6996480 | consumed tokens: 14328791040 | elapsed time per iteration (s): 0.25 | learning rate: 5.241E-05 | global batch size: 256 | lm loss: 2.907684E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1011.117 | TFLOPs: 6.44 | +31: iteration 27340/ 37905 | consumed samples: 6999040 | consumed tokens: 14334033920 | elapsed time per iteration (s): 0.26 | learning rate: 5.235E-05 | global batch size: 256 | lm loss: 2.902664E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 998.834 | TFLOPs: 6.36 | +31: iteration 27350/ 37905 | consumed samples: 7001600 | consumed tokens: 14339276800 | elapsed time per iteration (s): 0.24 | learning rate: 5.230E-05 | global batch size: 256 | lm loss: 2.898720E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.443 | TFLOPs: 6.93 | +31: iteration 27360/ 37905 | consumed samples: 7004160 | consumed tokens: 14344519680 | elapsed time per iteration (s): 0.23 | learning rate: 5.224E-05 | global batch size: 256 | lm loss: 2.913856E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.772 | TFLOPs: 7.11 | +31: iteration 27370/ 37905 | consumed samples: 7006720 | consumed tokens: 14349762560 | elapsed time per iteration (s): 0.21 | learning rate: 5.218E-05 | global batch size: 256 | lm loss: 2.963856E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.390 | TFLOPs: 7.75 | +31: iteration 27380/ 37905 | consumed samples: 7009280 | consumed tokens: 14355005440 | elapsed time per iteration (s): 0.23 | learning rate: 5.213E-05 | global batch size: 256 | lm loss: 2.886156E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.616 | TFLOPs: 7.11 | +31: iteration 27390/ 37905 | consumed samples: 7011840 | consumed tokens: 14360248320 | elapsed time per iteration (s): 0.20 | learning rate: 5.207E-05 | global batch size: 256 | lm loss: 2.913148E+00 | grad norm: 0.270 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.127 | TFLOPs: 7.96 | +31: iteration 27400/ 37905 | consumed samples: 7014400 | consumed tokens: 14365491200 | elapsed time per iteration (s): 0.21 | learning rate: 5.201E-05 | global batch size: 256 | lm loss: 2.886330E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.044 | TFLOPs: 7.59 | +31: iteration 27410/ 37905 | consumed samples: 7016960 | consumed tokens: 14370734080 | elapsed time per iteration (s): 0.21 | learning rate: 5.195E-05 | global batch size: 256 | lm loss: 2.901556E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.787 | TFLOPs: 7.90 | +31: iteration 27420/ 37905 | consumed samples: 7019520 | consumed tokens: 14375976960 | elapsed time per iteration (s): 0.25 | learning rate: 5.190E-05 | global batch size: 256 | lm loss: 2.925117E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.713 | TFLOPs: 6.45 | +31: iteration 27430/ 37905 | consumed samples: 7022080 | consumed tokens: 14381219840 | elapsed time per iteration (s): 0.23 | learning rate: 5.184E-05 | global batch size: 256 | lm loss: 2.925719E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.676 | TFLOPs: 6.97 | +31: iteration 27440/ 37905 | consumed samples: 7024640 | consumed tokens: 14386462720 | elapsed time per iteration (s): 0.22 | learning rate: 5.178E-05 | global batch size: 256 | lm loss: 2.912189E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.209 | TFLOPs: 7.37 | +31: iteration 27450/ 37905 | consumed samples: 7027200 | consumed tokens: 14391705600 | elapsed time per iteration (s): 0.24 | learning rate: 5.173E-05 | global batch size: 256 | lm loss: 2.903288E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.531 | TFLOPs: 6.84 | +31: iteration 27460/ 37905 | consumed samples: 7029760 | consumed tokens: 14396948480 | elapsed time per iteration (s): 0.22 | learning rate: 5.167E-05 | global batch size: 256 | lm loss: 2.937259E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.637 | TFLOPs: 7.51 | +31: iteration 27470/ 37905 | consumed samples: 7032320 | consumed tokens: 14402191360 | elapsed time per iteration (s): 0.19 | learning rate: 5.161E-05 | global batch size: 256 | lm loss: 2.902399E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1333.713 | TFLOPs: 8.49 | +31: iteration 27480/ 37905 | consumed samples: 7034880 | consumed tokens: 14407434240 | elapsed time per iteration (s): 0.21 | learning rate: 5.156E-05 | global batch size: 256 | lm loss: 2.898540E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.252 | TFLOPs: 7.68 | +31: iteration 27490/ 37905 | consumed samples: 7037440 | consumed tokens: 14412677120 | elapsed time per iteration (s): 0.21 | learning rate: 5.150E-05 | global batch size: 256 | lm loss: 2.919967E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.799 | TFLOPs: 7.75 | +31: iteration 27500/ 37905 | consumed samples: 7040000 | consumed tokens: 14417920000 | elapsed time per iteration (s): 0.19 | learning rate: 5.144E-05 | global batch size: 256 | lm loss: 2.928356E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1342.456 | TFLOPs: 8.55 | +31: iteration 27510/ 37905 | consumed samples: 7042560 | consumed tokens: 14423162880 | elapsed time per iteration (s): 0.19 | learning rate: 5.139E-05 | global batch size: 256 | lm loss: 2.932357E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.733 | TFLOPs: 8.43 | +31: iteration 27520/ 37905 | consumed samples: 7045120 | consumed tokens: 14428405760 | elapsed time per iteration (s): 0.22 | learning rate: 5.133E-05 | global batch size: 256 | lm loss: 2.888895E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.907 | TFLOPs: 7.37 | +31: iteration 27530/ 37905 | consumed samples: 7047680 | consumed tokens: 14433648640 | elapsed time per iteration (s): 0.23 | learning rate: 5.127E-05 | global batch size: 256 | lm loss: 2.917970E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.695 | TFLOPs: 7.12 | +31: iteration 27540/ 37905 | consumed samples: 7050240 | consumed tokens: 14438891520 | elapsed time per iteration (s): 0.20 | learning rate: 5.122E-05 | global batch size: 256 | lm loss: 2.892846E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1292.215 | TFLOPs: 8.23 | +31: iteration 27550/ 37905 | consumed samples: 7052800 | consumed tokens: 14444134400 | elapsed time per iteration (s): 0.21 | learning rate: 5.116E-05 | global batch size: 256 | lm loss: 2.892700E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.685 | TFLOPs: 7.76 | +31: iteration 27560/ 37905 | consumed samples: 7055360 | consumed tokens: 14449377280 | elapsed time per iteration (s): 0.23 | learning rate: 5.110E-05 | global batch size: 256 | lm loss: 2.914151E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.486 | TFLOPs: 6.94 | +31: iteration 27570/ 37905 | consumed samples: 7057920 | consumed tokens: 14454620160 | elapsed time per iteration (s): 0.21 | learning rate: 5.105E-05 | global batch size: 256 | lm loss: 2.898196E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1248.470 | TFLOPs: 7.95 | +31: iteration 27580/ 37905 | consumed samples: 7060480 | consumed tokens: 14459863040 | elapsed time per iteration (s): 0.22 | learning rate: 5.099E-05 | global batch size: 256 | lm loss: 2.913235E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.160 | TFLOPs: 7.58 | +31: iteration 27590/ 37905 | consumed samples: 7063040 | consumed tokens: 14465105920 | elapsed time per iteration (s): 0.21 | learning rate: 5.093E-05 | global batch size: 256 | lm loss: 2.912072E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.995 | TFLOPs: 7.68 | +31: iteration 27600/ 37905 | consumed samples: 7065600 | consumed tokens: 14470348800 | elapsed time per iteration (s): 0.21 | learning rate: 5.088E-05 | global batch size: 256 | lm loss: 2.924372E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.308 | TFLOPs: 7.81 | +31: iteration 27610/ 37905 | consumed samples: 7068160 | consumed tokens: 14475591680 | elapsed time per iteration (s): 0.22 | learning rate: 5.082E-05 | global batch size: 256 | lm loss: 2.900553E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.383 | TFLOPs: 7.56 | +31: iteration 27620/ 37905 | consumed samples: 7070720 | consumed tokens: 14480834560 | elapsed time per iteration (s): 0.23 | learning rate: 5.077E-05 | global batch size: 256 | lm loss: 2.907215E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.236 | TFLOPs: 7.13 | +31: iteration 27630/ 37905 | consumed samples: 7073280 | consumed tokens: 14486077440 | elapsed time per iteration (s): 0.22 | learning rate: 5.071E-05 | global batch size: 256 | lm loss: 2.923348E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.631 | TFLOPs: 7.56 | +31: iteration 27640/ 37905 | consumed samples: 7075840 | consumed tokens: 14491320320 | elapsed time per iteration (s): 0.23 | learning rate: 5.065E-05 | global batch size: 256 | lm loss: 2.916416E+00 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.637 | TFLOPs: 7.23 | +31: iteration 27650/ 37905 | consumed samples: 7078400 | consumed tokens: 14496563200 | elapsed time per iteration (s): 0.19 | learning rate: 5.060E-05 | global batch size: 256 | lm loss: 2.917967E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.648 | TFLOPs: 8.46 | +31: iteration 27660/ 37905 | consumed samples: 7080960 | consumed tokens: 14501806080 | elapsed time per iteration (s): 0.21 | learning rate: 5.054E-05 | global batch size: 256 | lm loss: 2.896441E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.389 | TFLOPs: 7.86 | +31: iteration 27670/ 37905 | consumed samples: 7083520 | consumed tokens: 14507048960 | elapsed time per iteration (s): 0.22 | learning rate: 5.049E-05 | global batch size: 256 | lm loss: 2.921903E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.615 | TFLOPs: 7.50 | +31: iteration 27680/ 37905 | consumed samples: 7086080 | consumed tokens: 14512291840 | elapsed time per iteration (s): 0.19 | learning rate: 5.043E-05 | global batch size: 256 | lm loss: 2.925065E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1376.344 | TFLOPs: 8.77 | +31: iteration 27690/ 37905 | consumed samples: 7088640 | consumed tokens: 14517534720 | elapsed time per iteration (s): 0.21 | learning rate: 5.037E-05 | global batch size: 256 | lm loss: 2.941444E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.935 | TFLOPs: 7.71 | +31: iteration 27700/ 37905 | consumed samples: 7091200 | consumed tokens: 14522777600 | elapsed time per iteration (s): 0.23 | learning rate: 5.032E-05 | global batch size: 256 | lm loss: 2.893203E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.850 | TFLOPs: 7.17 | +31: iteration 27710/ 37905 | consumed samples: 7093760 | consumed tokens: 14528020480 | elapsed time per iteration (s): 0.20 | learning rate: 5.026E-05 | global batch size: 256 | lm loss: 2.945666E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.963 | TFLOPs: 8.33 | +31: iteration 27720/ 37905 | consumed samples: 7096320 | consumed tokens: 14533263360 | elapsed time per iteration (s): 0.21 | learning rate: 5.021E-05 | global batch size: 256 | lm loss: 2.928102E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.833 | TFLOPs: 7.63 | +31: iteration 27730/ 37905 | consumed samples: 7098880 | consumed tokens: 14538506240 | elapsed time per iteration (s): 0.21 | learning rate: 5.015E-05 | global batch size: 256 | lm loss: 2.914824E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.764 | TFLOPs: 7.79 | +31: iteration 27740/ 37905 | consumed samples: 7101440 | consumed tokens: 14543749120 | elapsed time per iteration (s): 0.24 | learning rate: 5.010E-05 | global batch size: 256 | lm loss: 2.912106E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.128 | TFLOPs: 6.79 | +31: iteration 27750/ 37905 | consumed samples: 7104000 | consumed tokens: 14548992000 | elapsed time per iteration (s): 0.22 | learning rate: 5.004E-05 | global batch size: 256 | lm loss: 2.934845E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.694 | TFLOPs: 7.50 | +31: iteration 27760/ 37905 | consumed samples: 7106560 | consumed tokens: 14554234880 | elapsed time per iteration (s): 0.24 | learning rate: 4.998E-05 | global batch size: 256 | lm loss: 2.918170E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.165 | TFLOPs: 6.91 | +31: iteration 27770/ 37905 | consumed samples: 7109120 | consumed tokens: 14559477760 | elapsed time per iteration (s): 0.25 | learning rate: 4.993E-05 | global batch size: 256 | lm loss: 2.889149E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.252 | TFLOPs: 6.64 | +31: iteration 27780/ 37905 | consumed samples: 7111680 | consumed tokens: 14564720640 | elapsed time per iteration (s): 0.23 | learning rate: 4.987E-05 | global batch size: 256 | lm loss: 2.944563E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.039 | TFLOPs: 7.09 | +31: iteration 27790/ 37905 | consumed samples: 7114240 | consumed tokens: 14569963520 | elapsed time per iteration (s): 0.22 | learning rate: 4.982E-05 | global batch size: 256 | lm loss: 2.900390E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.614 | TFLOPs: 7.39 | +31: iteration 27800/ 37905 | consumed samples: 7116800 | consumed tokens: 14575206400 | elapsed time per iteration (s): 0.22 | learning rate: 4.976E-05 | global batch size: 256 | lm loss: 2.900951E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.511 | TFLOPs: 7.44 | +31: iteration 27810/ 37905 | consumed samples: 7119360 | consumed tokens: 14580449280 | elapsed time per iteration (s): 0.22 | learning rate: 4.971E-05 | global batch size: 256 | lm loss: 2.888979E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.489 | TFLOPs: 7.44 | +31: iteration 27820/ 37905 | consumed samples: 7121920 | consumed tokens: 14585692160 | elapsed time per iteration (s): 0.24 | learning rate: 4.965E-05 | global batch size: 256 | lm loss: 2.895798E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.379 | TFLOPs: 6.93 | +31: iteration 27830/ 37905 | consumed samples: 7124480 | consumed tokens: 14590935040 | elapsed time per iteration (s): 0.21 | learning rate: 4.960E-05 | global batch size: 256 | lm loss: 2.921153E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.027 | TFLOPs: 7.83 | +31: iteration 27840/ 37905 | consumed samples: 7127040 | consumed tokens: 14596177920 | elapsed time per iteration (s): 0.22 | learning rate: 4.954E-05 | global batch size: 256 | lm loss: 2.933151E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.978 | TFLOPs: 7.33 | +31: iteration 27850/ 37905 | consumed samples: 7129600 | consumed tokens: 14601420800 | elapsed time per iteration (s): 0.20 | learning rate: 4.949E-05 | global batch size: 256 | lm loss: 2.928426E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1260.214 | TFLOPs: 8.03 | +31: iteration 27860/ 37905 | consumed samples: 7132160 | consumed tokens: 14606663680 | elapsed time per iteration (s): 0.23 | learning rate: 4.943E-05 | global batch size: 256 | lm loss: 2.932233E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.395 | TFLOPs: 7.20 | +31: iteration 27870/ 37905 | consumed samples: 7134720 | consumed tokens: 14611906560 | elapsed time per iteration (s): 0.21 | learning rate: 4.938E-05 | global batch size: 256 | lm loss: 2.889269E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1248.247 | TFLOPs: 7.95 | +31: iteration 27880/ 37905 | consumed samples: 7137280 | consumed tokens: 14617149440 | elapsed time per iteration (s): 0.20 | learning rate: 4.932E-05 | global batch size: 256 | lm loss: 2.942627E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1262.329 | TFLOPs: 8.04 | +31: iteration 27890/ 37905 | consumed samples: 7139840 | consumed tokens: 14622392320 | elapsed time per iteration (s): 0.23 | learning rate: 4.926E-05 | global batch size: 256 | lm loss: 2.889832E+00 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.870 | TFLOPs: 7.14 | +31: iteration 27900/ 37905 | consumed samples: 7142400 | consumed tokens: 14627635200 | elapsed time per iteration (s): 0.22 | learning rate: 4.921E-05 | global batch size: 256 | lm loss: 2.861086E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.851 | TFLOPs: 7.55 | +31: iteration 27910/ 37905 | consumed samples: 7144960 | consumed tokens: 14632878080 | elapsed time per iteration (s): 0.24 | learning rate: 4.915E-05 | global batch size: 256 | lm loss: 2.900819E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.542 | TFLOPs: 6.69 | +31: iteration 27920/ 37905 | consumed samples: 7147520 | consumed tokens: 14638120960 | elapsed time per iteration (s): 0.22 | learning rate: 4.910E-05 | global batch size: 256 | lm loss: 2.882078E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.487 | TFLOPs: 7.45 | +31: iteration 27930/ 37905 | consumed samples: 7150080 | consumed tokens: 14643363840 | elapsed time per iteration (s): 0.22 | learning rate: 4.904E-05 | global batch size: 256 | lm loss: 2.895407E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.728 | TFLOPs: 7.56 | +31: iteration 27940/ 37905 | consumed samples: 7152640 | consumed tokens: 14648606720 | elapsed time per iteration (s): 0.22 | learning rate: 4.899E-05 | global batch size: 256 | lm loss: 2.955006E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.492 | TFLOPs: 7.30 | +31: iteration 27950/ 37905 | consumed samples: 7155200 | consumed tokens: 14653849600 | elapsed time per iteration (s): 0.24 | learning rate: 4.894E-05 | global batch size: 256 | lm loss: 2.914689E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.782 | TFLOPs: 6.78 | +31: iteration 27960/ 37905 | consumed samples: 7157760 | consumed tokens: 14659092480 | elapsed time per iteration (s): 0.20 | learning rate: 4.888E-05 | global batch size: 256 | lm loss: 2.901062E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1300.593 | TFLOPs: 8.28 | +31: iteration 27970/ 37905 | consumed samples: 7160320 | consumed tokens: 14664335360 | elapsed time per iteration (s): 0.24 | learning rate: 4.883E-05 | global batch size: 256 | lm loss: 2.907960E+00 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.116 | TFLOPs: 6.87 | +31: iteration 27980/ 37905 | consumed samples: 7162880 | consumed tokens: 14669578240 | elapsed time per iteration (s): 0.23 | learning rate: 4.877E-05 | global batch size: 256 | lm loss: 2.918885E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.766 | TFLOPs: 7.20 | +31: iteration 27990/ 37905 | consumed samples: 7165440 | consumed tokens: 14674821120 | elapsed time per iteration (s): 0.27 | learning rate: 4.872E-05 | global batch size: 256 | lm loss: 2.907727E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 943.097 | TFLOPs: 6.01 | + 0: [2022-11-24 15:52:52,983] [INFO] [logging.py:68:log_dist] [Rank 0] step=28000, skipped=0, lr=[4.866186028599282e-05, 4.866186028599282e-05, 4.866186028599282e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 28000/ 37905 | consumed samples: 7168000 | consumed tokens: 14680064000 | elapsed time per iteration (s): 0.28 | learning rate: 4.866E-05 | global batch size: 256 | lm loss: 2.905211E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 905.365 | TFLOPs: 5.77 | + 0: steps: 28000 loss: 2.9653 iter time (s): 0.222 samples/sec: 1152.955 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 28000 | lm loss value: 2.880991E+00 | lm loss PPL: 1.783193E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 28000 to checkpoints_83m + 0: [2022-11-24 15:52:53,175] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step28000 is begin to save! + 0: [2022-11-24 15:52:53,188] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,260] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,272] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,272] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,283] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,294] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,305] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,316] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,327] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,338] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,359] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,370] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,370] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:52:53,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:52:53,372] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step28000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:52:53,372] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:52:53,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:52:53,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step28000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:52:53,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:52:53,446] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:52:53,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +20: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:52:53,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 4: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 0: [2022-11-24 15:52:53,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 2: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,447] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:52:53,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +29: [2022-11-24 15:52:53,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,448] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +25: [2022-11-24 15:52:53,448] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:52:53,448] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +18: [2022-11-24 15:52:53,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:52:53,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:52:53,449] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:52:53,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,450] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 15:52:53,450] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:52:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +20: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +21: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +28: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 5: [2022-11-24 15:52:53,451] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:52:53,452] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,453] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 15:52:53,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +25: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 2: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,454] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +18: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +11: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +22: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 1: [2022-11-24 15:52:53,455] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,455] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:52:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +24: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 7: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,456] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:52:53,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +17: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:52:53,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +21: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 0: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,457] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 0: [2022-11-24 15:52:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:52:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 5: [2022-11-24 15:52:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:52:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +20: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,458] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:52:53,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +28: [2022-11-24 15:52:53,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,459] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 15:52:53,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:52:53,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 4: [2022-11-24 15:52:53,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,460] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:52:53,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +29: [2022-11-24 15:52:53,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +25: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +18: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:52:53,461] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 2: [2022-11-24 15:52:53,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:52:53,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:52:53,462] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,462] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:52:53,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 7: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,463] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +17: [2022-11-24 15:52:53,463] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:52:53,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:52:53,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 15:52:53,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +19: [2022-11-24 15:52:53,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,464] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,464] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +13: [2022-11-24 15:52:53,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 0: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:52:53,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +12: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:52:53,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +21: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,465] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 5: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:52:53,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +20: [2022-11-24 15:52:53,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:52:53,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:52:53,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,466] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:52:53,466] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +28: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 4: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,467] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,467] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:52:53,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,468] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +11: [2022-11-24 15:52:53,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +29: [2022-11-24 15:52:53,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +25: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 2: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +18: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,469] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:52:53,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:52:53,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 1: [2022-11-24 15:52:53,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:52:53,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +17: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:52:53,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:52:53,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +12: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 0: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:52:53,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +13: [2022-11-24 15:52:53,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +19: [2022-11-24 15:52:53,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +21: [2022-11-24 15:52:53,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +20: [2022-11-24 15:52:53,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 15:52:53,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:52:53,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 5: [2022-11-24 15:52:53,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 4: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +28: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 4: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:52:53,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:52:53,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +25: [2022-11-24 15:52:53,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +25: [2022-11-24 15:52:53,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +29: [2022-11-24 15:52:53,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +18: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +11: [2022-11-24 15:52:53,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 2: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:52:53,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 1: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:52:53,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:52:53,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:52:53,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 7: [2022-11-24 15:52:53,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:52:53,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +17: [2022-11-24 15:52:53,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +24: [2022-11-24 15:52:53,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:52:53,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:52:53,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:52:53,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +13: [2022-11-24 15:52:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +21: [2022-11-24 15:52:53,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:52:53,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +20: [2022-11-24 15:52:53,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 15:52:53,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 5: [2022-11-24 15:52:53,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:52:53,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:52:53,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:52:53,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 4: [2022-11-24 15:52:53,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:52:53,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:52:53,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +28: [2022-11-24 15:52:53,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:52:53,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +29: [2022-11-24 15:52:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +25: [2022-11-24 15:52:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +18: [2022-11-24 15:52:53,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:52:53,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:52:53,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +22: [2022-11-24 15:52:53,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 2: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:52:53,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 1: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:52:53,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 7: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:52:53,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:52:53,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +17: [2022-11-24 15:52:53,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +19: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +13: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +21: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +20: [2022-11-24 15:52:53,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:52:53,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:52:53,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 5: [2022-11-24 15:52:53,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:52:53,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:52:53,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:52:53,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 4: [2022-11-24 15:52:53,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +28: [2022-11-24 15:52:53,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 15:52:53,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:52:53,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +29: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +25: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:52:53,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 9: [2022-11-24 15:52:53,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 2: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:52:53,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 1: [2022-11-24 15:52:53,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:52:53,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +10: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 7: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +25: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +29: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +20: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +23: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +29: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +14: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +18: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +17: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +28: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +27: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +19: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +22: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +23: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +17: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +28: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +10: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +19: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 1: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 0: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +14: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 6: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +26: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +12: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:52:53,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +15: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +24: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +11: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +12: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +27: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +30: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +19: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +22: [2022-11-24 15:52:53,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +26: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +15: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +30: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +19: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +17: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +22: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 1: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 3: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 8: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +11: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +24: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +31: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:52:53,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 15:52:53,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +13: [2022-11-24 15:52:53,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +13: [2022-11-24 15:52:53,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:52:53,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:52:53,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +13: [2022-11-24 15:52:53,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +21: [2022-11-24 15:52:53,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:52:53,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 15:52:53,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! +16: [2022-11-24 15:52:53,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:52:53,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step28000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 15:52:53,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step28000 is ready now! + 0: successfully saved checkpoint at iteration 28000 to checkpoints_83m +31: time (ms) | save-checkpoint: 348.61 +31: iteration 28010/ 37905 | consumed samples: 7170560 | consumed tokens: 14685306880 | elapsed time per iteration (s): 0.32 | learning rate: 4.861E-05 | global batch size: 256 | lm loss: 2.931808E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 801.303 | TFLOPs: 5.10 | +31: iteration 28020/ 37905 | consumed samples: 7173120 | consumed tokens: 14690549760 | elapsed time per iteration (s): 0.21 | learning rate: 4.855E-05 | global batch size: 256 | lm loss: 2.865327E+00 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.841 | TFLOPs: 7.59 | +31: iteration 28030/ 37905 | consumed samples: 7175680 | consumed tokens: 14695792640 | elapsed time per iteration (s): 0.25 | learning rate: 4.850E-05 | global batch size: 256 | lm loss: 2.923722E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.377 | TFLOPs: 6.65 | +31: iteration 28040/ 37905 | consumed samples: 7178240 | consumed tokens: 14701035520 | elapsed time per iteration (s): 0.25 | learning rate: 4.844E-05 | global batch size: 256 | lm loss: 2.913961E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.758 | TFLOPs: 6.60 | +31: iteration 28050/ 37905 | consumed samples: 7180800 | consumed tokens: 14706278400 | elapsed time per iteration (s): 0.24 | learning rate: 4.839E-05 | global batch size: 256 | lm loss: 2.882167E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.073 | TFLOPs: 6.82 | +31: iteration 28060/ 37905 | consumed samples: 7183360 | consumed tokens: 14711521280 | elapsed time per iteration (s): 0.22 | learning rate: 4.834E-05 | global batch size: 256 | lm loss: 2.896784E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.942 | TFLOPs: 7.53 | +31: iteration 28070/ 37905 | consumed samples: 7185920 | consumed tokens: 14716764160 | elapsed time per iteration (s): 0.21 | learning rate: 4.828E-05 | global batch size: 256 | lm loss: 2.944196E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1229.160 | TFLOPs: 7.83 | +31: iteration 28080/ 37905 | consumed samples: 7188480 | consumed tokens: 14722007040 | elapsed time per iteration (s): 0.21 | learning rate: 4.823E-05 | global batch size: 256 | lm loss: 2.902168E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.753 | TFLOPs: 7.58 | +31: iteration 28090/ 37905 | consumed samples: 7191040 | consumed tokens: 14727249920 | elapsed time per iteration (s): 0.25 | learning rate: 4.817E-05 | global batch size: 256 | lm loss: 2.908898E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.972 | TFLOPs: 6.53 | +31: iteration 28100/ 37905 | consumed samples: 7193600 | consumed tokens: 14732492800 | elapsed time per iteration (s): 0.22 | learning rate: 4.812E-05 | global batch size: 256 | lm loss: 2.930981E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1155.094 | TFLOPs: 7.36 | +31: iteration 28110/ 37905 | consumed samples: 7196160 | consumed tokens: 14737735680 | elapsed time per iteration (s): 0.22 | learning rate: 4.806E-05 | global batch size: 256 | lm loss: 2.903105E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.627 | TFLOPs: 7.44 | +31: iteration 28120/ 37905 | consumed samples: 7198720 | consumed tokens: 14742978560 | elapsed time per iteration (s): 0.23 | learning rate: 4.801E-05 | global batch size: 256 | lm loss: 2.897935E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.824 | TFLOPs: 7.11 | +31: iteration 28130/ 37905 | consumed samples: 7201280 | consumed tokens: 14748221440 | elapsed time per iteration (s): 0.28 | learning rate: 4.796E-05 | global batch size: 256 | lm loss: 2.932117E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 910.065 | TFLOPs: 5.80 | +31: iteration 28140/ 37905 | consumed samples: 7203840 | consumed tokens: 14753464320 | elapsed time per iteration (s): 0.26 | learning rate: 4.790E-05 | global batch size: 256 | lm loss: 2.925204E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.675 | TFLOPs: 6.33 | +31: iteration 28150/ 37905 | consumed samples: 7206400 | consumed tokens: 14758707200 | elapsed time per iteration (s): 0.22 | learning rate: 4.785E-05 | global batch size: 256 | lm loss: 2.920216E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.376 | TFLOPs: 7.47 | +31: iteration 28160/ 37905 | consumed samples: 7208960 | consumed tokens: 14763950080 | elapsed time per iteration (s): 0.24 | learning rate: 4.779E-05 | global batch size: 256 | lm loss: 2.878297E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.377 | TFLOPs: 6.69 | +31: iteration 28170/ 37905 | consumed samples: 7211520 | consumed tokens: 14769192960 | elapsed time per iteration (s): 0.20 | learning rate: 4.774E-05 | global batch size: 256 | lm loss: 2.904011E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1268.351 | TFLOPs: 8.08 | +31: iteration 28180/ 37905 | consumed samples: 7214080 | consumed tokens: 14774435840 | elapsed time per iteration (s): 0.22 | learning rate: 4.769E-05 | global batch size: 256 | lm loss: 2.882082E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.210 | TFLOPs: 7.26 | +31: iteration 28190/ 37905 | consumed samples: 7216640 | consumed tokens: 14779678720 | elapsed time per iteration (s): 0.28 | learning rate: 4.763E-05 | global batch size: 256 | lm loss: 2.910583E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 904.741 | TFLOPs: 5.76 | +31: iteration 28200/ 37905 | consumed samples: 7219200 | consumed tokens: 14784921600 | elapsed time per iteration (s): 0.23 | learning rate: 4.758E-05 | global batch size: 256 | lm loss: 2.868636E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.783 | TFLOPs: 6.95 | +31: iteration 28210/ 37905 | consumed samples: 7221760 | consumed tokens: 14790164480 | elapsed time per iteration (s): 0.22 | learning rate: 4.752E-05 | global batch size: 256 | lm loss: 2.887783E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.361 | TFLOPs: 7.35 | +31: iteration 28220/ 37905 | consumed samples: 7224320 | consumed tokens: 14795407360 | elapsed time per iteration (s): 0.24 | learning rate: 4.747E-05 | global batch size: 256 | lm loss: 2.925164E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.656 | TFLOPs: 6.69 | +31: iteration 28230/ 37905 | consumed samples: 7226880 | consumed tokens: 14800650240 | elapsed time per iteration (s): 0.23 | learning rate: 4.742E-05 | global batch size: 256 | lm loss: 2.886045E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.987 | TFLOPs: 7.14 | +31: iteration 28240/ 37905 | consumed samples: 7229440 | consumed tokens: 14805893120 | elapsed time per iteration (s): 0.22 | learning rate: 4.736E-05 | global batch size: 256 | lm loss: 2.899633E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.490 | TFLOPs: 7.47 | +31: iteration 28250/ 37905 | consumed samples: 7232000 | consumed tokens: 14811136000 | elapsed time per iteration (s): 0.22 | learning rate: 4.731E-05 | global batch size: 256 | lm loss: 2.907598E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.852 | TFLOPs: 7.48 | +31: iteration 28260/ 37905 | consumed samples: 7234560 | consumed tokens: 14816378880 | elapsed time per iteration (s): 0.22 | learning rate: 4.726E-05 | global batch size: 256 | lm loss: 2.898632E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.980 | TFLOPs: 7.46 | +31: iteration 28270/ 37905 | consumed samples: 7237120 | consumed tokens: 14821621760 | elapsed time per iteration (s): 0.24 | learning rate: 4.720E-05 | global batch size: 256 | lm loss: 2.892815E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.264 | TFLOPs: 6.70 | +31: iteration 28280/ 37905 | consumed samples: 7239680 | consumed tokens: 14826864640 | elapsed time per iteration (s): 0.22 | learning rate: 4.715E-05 | global batch size: 256 | lm loss: 2.917404E+00 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1188.423 | TFLOPs: 7.57 | +31: iteration 28290/ 37905 | consumed samples: 7242240 | consumed tokens: 14832107520 | elapsed time per iteration (s): 0.21 | learning rate: 4.710E-05 | global batch size: 256 | lm loss: 2.923796E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.511 | TFLOPs: 7.75 | +31: iteration 28300/ 37905 | consumed samples: 7244800 | consumed tokens: 14837350400 | elapsed time per iteration (s): 0.20 | learning rate: 4.704E-05 | global batch size: 256 | lm loss: 2.903390E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.816 | TFLOPs: 8.18 | +31: iteration 28310/ 37905 | consumed samples: 7247360 | consumed tokens: 14842593280 | elapsed time per iteration (s): 0.22 | learning rate: 4.699E-05 | global batch size: 256 | lm loss: 2.938164E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.110 | TFLOPs: 7.31 | +31: iteration 28320/ 37905 | consumed samples: 7249920 | consumed tokens: 14847836160 | elapsed time per iteration (s): 0.20 | learning rate: 4.694E-05 | global batch size: 256 | lm loss: 2.974122E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.432 | TFLOPs: 8.14 | +31: iteration 28330/ 37905 | consumed samples: 7252480 | consumed tokens: 14853079040 | elapsed time per iteration (s): 0.26 | learning rate: 4.688E-05 | global batch size: 256 | lm loss: 2.935278E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 995.269 | TFLOPs: 6.34 | +31: iteration 28340/ 37905 | consumed samples: 7255040 | consumed tokens: 14858321920 | elapsed time per iteration (s): 0.24 | learning rate: 4.683E-05 | global batch size: 256 | lm loss: 2.910089E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.023 | TFLOPs: 6.88 | +31: iteration 28350/ 37905 | consumed samples: 7257600 | consumed tokens: 14863564800 | elapsed time per iteration (s): 0.21 | learning rate: 4.678E-05 | global batch size: 256 | lm loss: 2.891047E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.058 | TFLOPs: 7.72 | +31: iteration 28360/ 37905 | consumed samples: 7260160 | consumed tokens: 14868807680 | elapsed time per iteration (s): 0.26 | learning rate: 4.672E-05 | global batch size: 256 | lm loss: 2.920337E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 984.166 | TFLOPs: 6.27 | +31: iteration 28370/ 37905 | consumed samples: 7262720 | consumed tokens: 14874050560 | elapsed time per iteration (s): 0.24 | learning rate: 4.667E-05 | global batch size: 256 | lm loss: 2.927118E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.977 | TFLOPs: 6.87 | +31: iteration 28380/ 37905 | consumed samples: 7265280 | consumed tokens: 14879293440 | elapsed time per iteration (s): 0.31 | learning rate: 4.662E-05 | global batch size: 256 | lm loss: 2.883697E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 835.541 | TFLOPs: 5.32 | +31: iteration 28390/ 37905 | consumed samples: 7267840 | consumed tokens: 14884536320 | elapsed time per iteration (s): 0.23 | learning rate: 4.657E-05 | global batch size: 256 | lm loss: 2.899730E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.373 | TFLOPs: 7.21 | +31: iteration 28400/ 37905 | consumed samples: 7270400 | consumed tokens: 14889779200 | elapsed time per iteration (s): 0.23 | learning rate: 4.651E-05 | global batch size: 256 | lm loss: 2.927688E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1108.417 | TFLOPs: 7.06 | +31: iteration 28410/ 37905 | consumed samples: 7272960 | consumed tokens: 14895022080 | elapsed time per iteration (s): 0.24 | learning rate: 4.646E-05 | global batch size: 256 | lm loss: 2.908018E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.483 | TFLOPs: 6.77 | +31: iteration 28420/ 37905 | consumed samples: 7275520 | consumed tokens: 14900264960 | elapsed time per iteration (s): 0.22 | learning rate: 4.641E-05 | global batch size: 256 | lm loss: 2.949985E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.552 | TFLOPs: 7.47 | +31: iteration 28430/ 37905 | consumed samples: 7278080 | consumed tokens: 14905507840 | elapsed time per iteration (s): 0.23 | learning rate: 4.635E-05 | global batch size: 256 | lm loss: 2.884342E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.378 | TFLOPs: 7.13 | +31: iteration 28440/ 37905 | consumed samples: 7280640 | consumed tokens: 14910750720 | elapsed time per iteration (s): 0.25 | learning rate: 4.630E-05 | global batch size: 256 | lm loss: 2.895203E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.662 | TFLOPs: 6.65 | +31: iteration 28450/ 37905 | consumed samples: 7283200 | consumed tokens: 14915993600 | elapsed time per iteration (s): 0.20 | learning rate: 4.625E-05 | global batch size: 256 | lm loss: 2.869970E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.465 | TFLOPs: 8.00 | +31: iteration 28460/ 37905 | consumed samples: 7285760 | consumed tokens: 14921236480 | elapsed time per iteration (s): 0.20 | learning rate: 4.620E-05 | global batch size: 256 | lm loss: 2.896249E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.991 | TFLOPs: 8.22 | +31: iteration 28470/ 37905 | consumed samples: 7288320 | consumed tokens: 14926479360 | elapsed time per iteration (s): 0.24 | learning rate: 4.614E-05 | global batch size: 256 | lm loss: 2.864269E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1047.602 | TFLOPs: 6.67 | +31: iteration 28480/ 37905 | consumed samples: 7290880 | consumed tokens: 14931722240 | elapsed time per iteration (s): 0.22 | learning rate: 4.609E-05 | global batch size: 256 | lm loss: 2.905623E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.521 | TFLOPs: 7.54 | +31: iteration 28490/ 37905 | consumed samples: 7293440 | consumed tokens: 14936965120 | elapsed time per iteration (s): 0.22 | learning rate: 4.604E-05 | global batch size: 256 | lm loss: 2.910079E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.620 | TFLOPs: 7.46 | +31: iteration 28500/ 37905 | consumed samples: 7296000 | consumed tokens: 14942208000 | elapsed time per iteration (s): 0.25 | learning rate: 4.599E-05 | global batch size: 256 | lm loss: 2.922358E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1019.599 | TFLOPs: 6.49 | +31: iteration 28510/ 37905 | consumed samples: 7298560 | consumed tokens: 14947450880 | elapsed time per iteration (s): 0.24 | learning rate: 4.593E-05 | global batch size: 256 | lm loss: 2.915669E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.943 | TFLOPs: 6.92 | +31: iteration 28520/ 37905 | consumed samples: 7301120 | consumed tokens: 14952693760 | elapsed time per iteration (s): 0.23 | learning rate: 4.588E-05 | global batch size: 256 | lm loss: 2.929634E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.977 | TFLOPs: 6.97 | +31: iteration 28530/ 37905 | consumed samples: 7303680 | consumed tokens: 14957936640 | elapsed time per iteration (s): 0.23 | learning rate: 4.583E-05 | global batch size: 256 | lm loss: 2.886897E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.222 | TFLOPs: 7.12 | +31: iteration 28540/ 37905 | consumed samples: 7306240 | consumed tokens: 14963179520 | elapsed time per iteration (s): 0.24 | learning rate: 4.578E-05 | global batch size: 256 | lm loss: 2.914519E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.125 | TFLOPs: 6.78 | +31: iteration 28550/ 37905 | consumed samples: 7308800 | consumed tokens: 14968422400 | elapsed time per iteration (s): 0.23 | learning rate: 4.572E-05 | global batch size: 256 | lm loss: 2.908806E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.596 | TFLOPs: 7.12 | +31: iteration 28560/ 37905 | consumed samples: 7311360 | consumed tokens: 14973665280 | elapsed time per iteration (s): 0.20 | learning rate: 4.567E-05 | global batch size: 256 | lm loss: 2.914960E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.610 | TFLOPs: 8.05 | +31: iteration 28570/ 37905 | consumed samples: 7313920 | consumed tokens: 14978908160 | elapsed time per iteration (s): 0.21 | learning rate: 4.562E-05 | global batch size: 256 | lm loss: 2.886522E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.794 | TFLOPs: 7.92 | +31: iteration 28580/ 37905 | consumed samples: 7316480 | consumed tokens: 14984151040 | elapsed time per iteration (s): 0.20 | learning rate: 4.557E-05 | global batch size: 256 | lm loss: 2.909776E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.404 | TFLOPs: 8.08 | +31: iteration 28590/ 37905 | consumed samples: 7319040 | consumed tokens: 14989393920 | elapsed time per iteration (s): 0.21 | learning rate: 4.552E-05 | global batch size: 256 | lm loss: 2.899138E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.110 | TFLOPs: 7.61 | +31: iteration 28600/ 37905 | consumed samples: 7321600 | consumed tokens: 14994636800 | elapsed time per iteration (s): 0.24 | learning rate: 4.546E-05 | global batch size: 256 | lm loss: 2.922163E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.305 | TFLOPs: 6.89 | +31: iteration 28610/ 37905 | consumed samples: 7324160 | consumed tokens: 14999879680 | elapsed time per iteration (s): 0.23 | learning rate: 4.541E-05 | global batch size: 256 | lm loss: 2.905296E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.036 | TFLOPs: 7.03 | +31: iteration 28620/ 37905 | consumed samples: 7326720 | consumed tokens: 15005122560 | elapsed time per iteration (s): 0.23 | learning rate: 4.536E-05 | global batch size: 256 | lm loss: 2.904802E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.911 | TFLOPs: 6.99 | +31: iteration 28630/ 37905 | consumed samples: 7329280 | consumed tokens: 15010365440 | elapsed time per iteration (s): 0.21 | learning rate: 4.531E-05 | global batch size: 256 | lm loss: 2.907868E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.601 | TFLOPs: 7.80 | +31: iteration 28640/ 37905 | consumed samples: 7331840 | consumed tokens: 15015608320 | elapsed time per iteration (s): 0.22 | learning rate: 4.526E-05 | global batch size: 256 | lm loss: 2.917127E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.895 | TFLOPs: 7.37 | +31: iteration 28650/ 37905 | consumed samples: 7334400 | consumed tokens: 15020851200 | elapsed time per iteration (s): 0.23 | learning rate: 4.520E-05 | global batch size: 256 | lm loss: 2.889574E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.708 | TFLOPs: 7.21 | +31: iteration 28660/ 37905 | consumed samples: 7336960 | consumed tokens: 15026094080 | elapsed time per iteration (s): 0.22 | learning rate: 4.515E-05 | global batch size: 256 | lm loss: 2.925045E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.305 | TFLOPs: 7.42 | +31: iteration 28670/ 37905 | consumed samples: 7339520 | consumed tokens: 15031336960 | elapsed time per iteration (s): 0.21 | learning rate: 4.510E-05 | global batch size: 256 | lm loss: 2.906225E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.773 | TFLOPs: 7.61 | +31: iteration 28680/ 37905 | consumed samples: 7342080 | consumed tokens: 15036579840 | elapsed time per iteration (s): 0.22 | learning rate: 4.505E-05 | global batch size: 256 | lm loss: 2.917772E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.108 | TFLOPs: 7.30 | +31: iteration 28690/ 37905 | consumed samples: 7344640 | consumed tokens: 15041822720 | elapsed time per iteration (s): 0.25 | learning rate: 4.500E-05 | global batch size: 256 | lm loss: 2.899209E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1031.087 | TFLOPs: 6.57 | +31: iteration 28700/ 37905 | consumed samples: 7347200 | consumed tokens: 15047065600 | elapsed time per iteration (s): 0.21 | learning rate: 4.495E-05 | global batch size: 256 | lm loss: 2.934579E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1248.132 | TFLOPs: 7.95 | +31: iteration 28710/ 37905 | consumed samples: 7349760 | consumed tokens: 15052308480 | elapsed time per iteration (s): 0.24 | learning rate: 4.489E-05 | global batch size: 256 | lm loss: 2.893671E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.191 | TFLOPs: 6.76 | +31: iteration 28720/ 37905 | consumed samples: 7352320 | consumed tokens: 15057551360 | elapsed time per iteration (s): 0.22 | learning rate: 4.484E-05 | global batch size: 256 | lm loss: 2.916735E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.494 | TFLOPs: 7.40 | +31: iteration 28730/ 37905 | consumed samples: 7354880 | consumed tokens: 15062794240 | elapsed time per iteration (s): 0.22 | learning rate: 4.479E-05 | global batch size: 256 | lm loss: 2.929196E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.122 | TFLOPs: 7.33 | +31: iteration 28740/ 37905 | consumed samples: 7357440 | consumed tokens: 15068037120 | elapsed time per iteration (s): 0.23 | learning rate: 4.474E-05 | global batch size: 256 | lm loss: 2.940294E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.513 | TFLOPs: 7.23 | +31: iteration 28750/ 37905 | consumed samples: 7360000 | consumed tokens: 15073280000 | elapsed time per iteration (s): 0.25 | learning rate: 4.469E-05 | global batch size: 256 | lm loss: 2.934484E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1007.914 | TFLOPs: 6.42 | +31: iteration 28760/ 37905 | consumed samples: 7362560 | consumed tokens: 15078522880 | elapsed time per iteration (s): 0.20 | learning rate: 4.464E-05 | global batch size: 256 | lm loss: 2.918101E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.540 | TFLOPs: 8.14 | +31: iteration 28770/ 37905 | consumed samples: 7365120 | consumed tokens: 15083765760 | elapsed time per iteration (s): 0.27 | learning rate: 4.459E-05 | global batch size: 256 | lm loss: 2.909617E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 961.572 | TFLOPs: 6.12 | +31: iteration 28780/ 37905 | consumed samples: 7367680 | consumed tokens: 15089008640 | elapsed time per iteration (s): 0.21 | learning rate: 4.454E-05 | global batch size: 256 | lm loss: 2.916982E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.055 | TFLOPs: 7.59 | +31: iteration 28790/ 37905 | consumed samples: 7370240 | consumed tokens: 15094251520 | elapsed time per iteration (s): 0.22 | learning rate: 4.448E-05 | global batch size: 256 | lm loss: 2.904968E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.363 | TFLOPs: 7.35 | +31: iteration 28800/ 37905 | consumed samples: 7372800 | consumed tokens: 15099494400 | elapsed time per iteration (s): 0.21 | learning rate: 4.443E-05 | global batch size: 256 | lm loss: 2.921723E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.373 | TFLOPs: 7.85 | +31: iteration 28810/ 37905 | consumed samples: 7375360 | consumed tokens: 15104737280 | elapsed time per iteration (s): 0.23 | learning rate: 4.438E-05 | global batch size: 256 | lm loss: 2.892688E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.638 | TFLOPs: 7.23 | +31: iteration 28820/ 37905 | consumed samples: 7377920 | consumed tokens: 15109980160 | elapsed time per iteration (s): 0.22 | learning rate: 4.433E-05 | global batch size: 256 | lm loss: 2.884594E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.769 | TFLOPs: 7.55 | +31: iteration 28830/ 37905 | consumed samples: 7380480 | consumed tokens: 15115223040 | elapsed time per iteration (s): 0.23 | learning rate: 4.428E-05 | global batch size: 256 | lm loss: 2.915043E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.270 | TFLOPs: 6.98 | +31: iteration 28840/ 37905 | consumed samples: 7383040 | consumed tokens: 15120465920 | elapsed time per iteration (s): 0.21 | learning rate: 4.423E-05 | global batch size: 256 | lm loss: 2.890024E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.833 | TFLOPs: 7.71 | +31: iteration 28850/ 37905 | consumed samples: 7385600 | consumed tokens: 15125708800 | elapsed time per iteration (s): 0.26 | learning rate: 4.418E-05 | global batch size: 256 | lm loss: 2.929379E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.038 | TFLOPs: 6.32 | +31: iteration 28860/ 37905 | consumed samples: 7388160 | consumed tokens: 15130951680 | elapsed time per iteration (s): 0.19 | learning rate: 4.413E-05 | global batch size: 256 | lm loss: 2.903228E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1325.488 | TFLOPs: 8.44 | +31: iteration 28870/ 37905 | consumed samples: 7390720 | consumed tokens: 15136194560 | elapsed time per iteration (s): 0.20 | learning rate: 4.408E-05 | global batch size: 256 | lm loss: 2.903350E+00 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.795 | TFLOPs: 8.06 | +31: iteration 28880/ 37905 | consumed samples: 7393280 | consumed tokens: 15141437440 | elapsed time per iteration (s): 0.23 | learning rate: 4.403E-05 | global batch size: 256 | lm loss: 2.917162E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1114.374 | TFLOPs: 7.10 | +31: iteration 28890/ 37905 | consumed samples: 7395840 | consumed tokens: 15146680320 | elapsed time per iteration (s): 0.24 | learning rate: 4.397E-05 | global batch size: 256 | lm loss: 2.914887E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.404 | TFLOPs: 6.85 | +31: iteration 28900/ 37905 | consumed samples: 7398400 | consumed tokens: 15151923200 | elapsed time per iteration (s): 0.22 | learning rate: 4.392E-05 | global batch size: 256 | lm loss: 2.913381E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.462 | TFLOPs: 7.40 | +31: iteration 28910/ 37905 | consumed samples: 7400960 | consumed tokens: 15157166080 | elapsed time per iteration (s): 0.21 | learning rate: 4.387E-05 | global batch size: 256 | lm loss: 2.918485E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.937 | TFLOPs: 7.89 | +31: iteration 28920/ 37905 | consumed samples: 7403520 | consumed tokens: 15162408960 | elapsed time per iteration (s): 0.19 | learning rate: 4.382E-05 | global batch size: 256 | lm loss: 2.932702E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.530 | TFLOPs: 8.47 | +31: iteration 28930/ 37905 | consumed samples: 7406080 | consumed tokens: 15167651840 | elapsed time per iteration (s): 0.23 | learning rate: 4.377E-05 | global batch size: 256 | lm loss: 2.905866E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.017 | TFLOPs: 7.21 | +31: iteration 28940/ 37905 | consumed samples: 7408640 | consumed tokens: 15172894720 | elapsed time per iteration (s): 0.22 | learning rate: 4.372E-05 | global batch size: 256 | lm loss: 2.939865E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.514 | TFLOPs: 7.45 | +31: iteration 28950/ 37905 | consumed samples: 7411200 | consumed tokens: 15178137600 | elapsed time per iteration (s): 0.22 | learning rate: 4.367E-05 | global batch size: 256 | lm loss: 2.927749E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.102 | TFLOPs: 7.57 | +31: iteration 28960/ 37905 | consumed samples: 7413760 | consumed tokens: 15183380480 | elapsed time per iteration (s): 0.22 | learning rate: 4.362E-05 | global batch size: 256 | lm loss: 2.874560E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.305 | TFLOPs: 7.56 | +31: iteration 28970/ 37905 | consumed samples: 7416320 | consumed tokens: 15188623360 | elapsed time per iteration (s): 0.23 | learning rate: 4.357E-05 | global batch size: 256 | lm loss: 2.955082E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1129.432 | TFLOPs: 7.19 | +31: iteration 28980/ 37905 | consumed samples: 7418880 | consumed tokens: 15193866240 | elapsed time per iteration (s): 0.20 | learning rate: 4.352E-05 | global batch size: 256 | lm loss: 2.949216E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.430 | TFLOPs: 8.08 | +31: iteration 28990/ 37905 | consumed samples: 7421440 | consumed tokens: 15199109120 | elapsed time per iteration (s): 0.29 | learning rate: 4.347E-05 | global batch size: 256 | lm loss: 2.919398E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 889.903 | TFLOPs: 5.67 | +31: iteration 29000/ 37905 | consumed samples: 7424000 | consumed tokens: 15204352000 | elapsed time per iteration (s): 0.21 | learning rate: 4.342E-05 | global batch size: 256 | lm loss: 2.894186E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.259 | TFLOPs: 7.62 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 29000 | lm loss value: 2.922443E+00 | lm loss PPL: 1.858664E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 29000 to checkpoints_83m + 0: [2022-11-24 15:56:41,267] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step29000 is begin to save! + 0: [2022-11-24 15:56:41,277] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,349] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,371] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,404] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,415] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,437] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,448] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,459] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 15:56:41,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 15:56:41,460] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step29000/mp_rank_00_model_states.pt + 0: [2022-11-24 15:56:41,460] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/mp_rank_00_model_states.pt... + 0: [2022-11-24 15:56:41,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/mp_rank_00_model_states.pt. + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +17: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... + 9: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +31: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +19: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 1: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 15:56:41,527] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step29000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 7: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:56:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 2: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +12: [2022-11-24 15:56:41,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 15:56:41,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:56:41,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:56:41,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: [2022-11-24 15:56:41,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +27: [2022-11-24 15:56:41,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:56:41,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:56:41,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +15: [2022-11-24 15:56:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 15:56:41,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 15:56:41,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:56:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +18: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:56:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:56:41,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:56:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 1: [2022-11-24 15:56:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +12: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 2: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:56:41,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 6: [2022-11-24 15:56:41,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:56:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +30: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:56:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:56:41,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +11: [2022-11-24 15:56:41,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 15:56:41,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:56:41,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +27: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:56:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:56:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +20: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +15: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:56:41,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 15:56:41,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +31: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 5: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:56:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:56:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:56:41,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:56:41,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:56:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: [2022-11-24 15:56:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 2: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:56:41,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 6: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:56:41,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 1: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:56:41,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +12: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 15:56:41,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:56:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +18: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:56:41,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:56:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +30: [2022-11-24 15:56:41,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 15:56:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 3: [2022-11-24 15:56:41,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 15:56:41,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +15: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +27: [2022-11-24 15:56:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:56:41,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:56:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +31: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 5: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:56:41,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:56:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 15:56:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:56:41,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:56:41,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: [2022-11-24 15:56:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:56:41,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 1: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 2: [2022-11-24 15:56:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 6: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +12: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:56:41,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 15:56:41,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:56:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 3: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:56:41,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 15:56:41,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +30: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +15: [2022-11-24 15:56:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:56:41,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +27: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:56:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:56:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 5: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:56:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +31: [2022-11-24 15:56:41,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +31: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:56:41,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +19: [2022-11-24 15:56:41,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:56:41,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:56:41,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:56:41,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:56:41,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 1: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:56:41,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 2: [2022-11-24 15:56:41,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 6: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:56:41,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +12: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +18: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:56:41,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:56:41,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 15:56:41,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:56:41,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:56:41,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +30: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 3: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:56:41,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 15:56:41,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +15: [2022-11-24 15:56:41,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 15:56:41,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +27: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:56:41,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:56:41,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 5: [2022-11-24 15:56:41,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:56:41,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 15:56:41,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +31: [2022-11-24 15:56:41,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:56:41,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:56:41,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:56:41,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: [2022-11-24 15:56:41,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:56:41,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:56:41,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 1: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 2: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:56:41,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 6: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:56:41,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +12: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:56:41,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:56:41,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +18: [2022-11-24 15:56:41,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,572] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,572] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:56:41,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:56:41,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:56:41,573] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 15:56:41,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 3: [2022-11-24 15:56:41,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +30: [2022-11-24 15:56:41,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 15:56:41,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,574] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:56:41,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:56:41,575] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +27: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:56:41,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +15: [2022-11-24 15:56:41,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +15: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:56:41,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 5: [2022-11-24 15:56:41,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:56:41,576] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:56:41,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +31: [2022-11-24 15:56:41,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,577] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 15:56:41,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: [2022-11-24 15:56:41,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:56:41,578] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:56:41,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 1: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 2: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 6: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:56:41,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +18: [2022-11-24 15:56:41,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,579] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +24: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:56:41,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,580] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:56:41,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 15:56:41,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 3: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +30: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,581] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 15:56:41,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +12: [2022-11-24 15:56:41,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 15:56:41,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,582] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 15:56:41,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:56:41,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +15: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,583] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +27: [2022-11-24 15:56:41,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:56:41,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +31: [2022-11-24 15:56:41,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,584] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 5: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 3: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +31: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +27: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt + 3: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +27: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 3: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +26: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +21: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. + 7: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +18: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt + 0: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 2: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 8: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +15: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +24: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +21: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +18: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +25: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 2: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 8: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +20: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +24: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +17: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 9: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +28: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. + 0: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 8: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 4: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +26: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +15: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 7: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +17: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt + 9: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +31: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +25: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt + 1: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +13: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. + 4: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +26: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +17: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 9: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +12: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +29: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +31: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +25: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +30: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +19: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 1: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +14: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +13: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt + 4: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +26: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +23: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +12: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +29: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +28: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +10: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +30: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +14: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 6: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +13: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +21: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +23: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +11: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +29: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 5: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +10: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +30: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +22: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 6: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +20: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +23: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt + 5: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,585] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +10: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +16: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +19: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +22: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +21: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +28: [2022-11-24 15:56:41,585] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! +11: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 15:56:41,586] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step29000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 15:56:41,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step29000 is ready now! + 0: successfully saved checkpoint at iteration 29000 to checkpoints_83m +31: time (ms) | save-checkpoint: 325.76 +31: iteration 29010/ 37905 | consumed samples: 7426560 | consumed tokens: 15209594880 | elapsed time per iteration (s): 0.23 | learning rate: 4.337E-05 | global batch size: 256 | lm loss: 2.860061E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.541 | TFLOPs: 7.12 | +31: iteration 29020/ 37905 | consumed samples: 7429120 | consumed tokens: 15214837760 | elapsed time per iteration (s): 0.20 | learning rate: 4.332E-05 | global batch size: 256 | lm loss: 2.913796E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1278.163 | TFLOPs: 8.14 | +31: iteration 29030/ 37905 | consumed samples: 7431680 | consumed tokens: 15220080640 | elapsed time per iteration (s): 0.22 | learning rate: 4.327E-05 | global batch size: 256 | lm loss: 2.896772E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.462 | TFLOPs: 7.26 | +31: iteration 29040/ 37905 | consumed samples: 7434240 | consumed tokens: 15225323520 | elapsed time per iteration (s): 0.21 | learning rate: 4.322E-05 | global batch size: 256 | lm loss: 2.887293E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.947 | TFLOPs: 7.74 | +31: iteration 29050/ 37905 | consumed samples: 7436800 | consumed tokens: 15230566400 | elapsed time per iteration (s): 0.22 | learning rate: 4.317E-05 | global batch size: 256 | lm loss: 2.923363E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.432 | TFLOPs: 7.42 | +31: iteration 29060/ 37905 | consumed samples: 7439360 | consumed tokens: 15235809280 | elapsed time per iteration (s): 0.24 | learning rate: 4.312E-05 | global batch size: 256 | lm loss: 2.918433E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.890 | TFLOPs: 6.71 | +31: iteration 29070/ 37905 | consumed samples: 7441920 | consumed tokens: 15241052160 | elapsed time per iteration (s): 0.24 | learning rate: 4.307E-05 | global batch size: 256 | lm loss: 2.892168E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.935 | TFLOPs: 6.68 | +31: iteration 29080/ 37905 | consumed samples: 7444480 | consumed tokens: 15246295040 | elapsed time per iteration (s): 0.24 | learning rate: 4.302E-05 | global batch size: 256 | lm loss: 2.932887E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.198 | TFLOPs: 6.66 | +31: iteration 29090/ 37905 | consumed samples: 7447040 | consumed tokens: 15251537920 | elapsed time per iteration (s): 0.25 | learning rate: 4.297E-05 | global batch size: 256 | lm loss: 2.916544E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.491 | TFLOPs: 6.64 | +31: iteration 29100/ 37905 | consumed samples: 7449600 | consumed tokens: 15256780800 | elapsed time per iteration (s): 0.22 | learning rate: 4.292E-05 | global batch size: 256 | lm loss: 2.875167E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.887 | TFLOPs: 7.33 | +31: iteration 29110/ 37905 | consumed samples: 7452160 | consumed tokens: 15262023680 | elapsed time per iteration (s): 0.21 | learning rate: 4.287E-05 | global batch size: 256 | lm loss: 2.906477E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.143 | TFLOPs: 7.93 | +31: iteration 29120/ 37905 | consumed samples: 7454720 | consumed tokens: 15267266560 | elapsed time per iteration (s): 0.20 | learning rate: 4.282E-05 | global batch size: 256 | lm loss: 2.890621E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.570 | TFLOPs: 7.98 | +31: iteration 29130/ 37905 | consumed samples: 7457280 | consumed tokens: 15272509440 | elapsed time per iteration (s): 0.24 | learning rate: 4.277E-05 | global batch size: 256 | lm loss: 2.900300E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.104 | TFLOPs: 6.87 | +31: iteration 29140/ 37905 | consumed samples: 7459840 | consumed tokens: 15277752320 | elapsed time per iteration (s): 0.21 | learning rate: 4.272E-05 | global batch size: 256 | lm loss: 2.894472E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.633 | TFLOPs: 7.75 | +31: iteration 29150/ 37905 | consumed samples: 7462400 | consumed tokens: 15282995200 | elapsed time per iteration (s): 0.19 | learning rate: 4.267E-05 | global batch size: 256 | lm loss: 2.923057E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1345.772 | TFLOPs: 8.57 | +31: iteration 29160/ 37905 | consumed samples: 7464960 | consumed tokens: 15288238080 | elapsed time per iteration (s): 0.22 | learning rate: 4.262E-05 | global batch size: 256 | lm loss: 2.905435E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.228 | TFLOPs: 7.53 | +31: iteration 29170/ 37905 | consumed samples: 7467520 | consumed tokens: 15293480960 | elapsed time per iteration (s): 0.22 | learning rate: 4.257E-05 | global batch size: 256 | lm loss: 2.891923E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.345 | TFLOPs: 7.28 | +31: iteration 29180/ 37905 | consumed samples: 7470080 | consumed tokens: 15298723840 | elapsed time per iteration (s): 0.20 | learning rate: 4.252E-05 | global batch size: 256 | lm loss: 2.919089E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.138 | TFLOPs: 8.06 | +31: iteration 29190/ 37905 | consumed samples: 7472640 | consumed tokens: 15303966720 | elapsed time per iteration (s): 0.23 | learning rate: 4.247E-05 | global batch size: 256 | lm loss: 2.902485E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.549 | TFLOPs: 7.02 | +31: iteration 29200/ 37905 | consumed samples: 7475200 | consumed tokens: 15309209600 | elapsed time per iteration (s): 0.23 | learning rate: 4.243E-05 | global batch size: 256 | lm loss: 2.851904E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.403 | TFLOPs: 7.15 | +31: iteration 29210/ 37905 | consumed samples: 7477760 | consumed tokens: 15314452480 | elapsed time per iteration (s): 0.20 | learning rate: 4.238E-05 | global batch size: 256 | lm loss: 2.926334E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.390 | TFLOPs: 8.10 | +31: iteration 29220/ 37905 | consumed samples: 7480320 | consumed tokens: 15319695360 | elapsed time per iteration (s): 0.23 | learning rate: 4.233E-05 | global batch size: 256 | lm loss: 2.908586E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.462 | TFLOPs: 7.07 | +31: iteration 29230/ 37905 | consumed samples: 7482880 | consumed tokens: 15324938240 | elapsed time per iteration (s): 0.23 | learning rate: 4.228E-05 | global batch size: 256 | lm loss: 2.878407E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.915 | TFLOPs: 7.13 | +31: iteration 29240/ 37905 | consumed samples: 7485440 | consumed tokens: 15330181120 | elapsed time per iteration (s): 0.22 | learning rate: 4.223E-05 | global batch size: 256 | lm loss: 2.901040E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.967 | TFLOPs: 7.29 | +31: iteration 29250/ 37905 | consumed samples: 7488000 | consumed tokens: 15335424000 | elapsed time per iteration (s): 0.21 | learning rate: 4.218E-05 | global batch size: 256 | lm loss: 2.879128E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.366 | TFLOPs: 7.81 | +31: iteration 29260/ 37905 | consumed samples: 7490560 | consumed tokens: 15340666880 | elapsed time per iteration (s): 0.28 | learning rate: 4.213E-05 | global batch size: 256 | lm loss: 2.893617E+00 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 917.153 | TFLOPs: 5.84 | +31: iteration 29270/ 37905 | consumed samples: 7493120 | consumed tokens: 15345909760 | elapsed time per iteration (s): 0.21 | learning rate: 4.208E-05 | global batch size: 256 | lm loss: 2.904539E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.271 | TFLOPs: 7.78 | +31: iteration 29280/ 37905 | consumed samples: 7495680 | consumed tokens: 15351152640 | elapsed time per iteration (s): 0.21 | learning rate: 4.203E-05 | global batch size: 256 | lm loss: 2.915221E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.503 | TFLOPs: 7.76 | +31: iteration 29290/ 37905 | consumed samples: 7498240 | consumed tokens: 15356395520 | elapsed time per iteration (s): 0.22 | learning rate: 4.198E-05 | global batch size: 256 | lm loss: 2.895049E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.029 | TFLOPs: 7.36 | +31: iteration 29300/ 37905 | consumed samples: 7500800 | consumed tokens: 15361638400 | elapsed time per iteration (s): 0.21 | learning rate: 4.194E-05 | global batch size: 256 | lm loss: 2.913911E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.456 | TFLOPs: 7.89 | +31: iteration 29310/ 37905 | consumed samples: 7503360 | consumed tokens: 15366881280 | elapsed time per iteration (s): 0.20 | learning rate: 4.189E-05 | global batch size: 256 | lm loss: 2.867855E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1263.482 | TFLOPs: 8.05 | +31: iteration 29320/ 37905 | consumed samples: 7505920 | consumed tokens: 15372124160 | elapsed time per iteration (s): 0.25 | learning rate: 4.184E-05 | global batch size: 256 | lm loss: 2.932248E+00 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.834 | TFLOPs: 6.60 | +31: iteration 29330/ 37905 | consumed samples: 7508480 | consumed tokens: 15377367040 | elapsed time per iteration (s): 0.31 | learning rate: 4.179E-05 | global batch size: 256 | lm loss: 2.899479E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.819 | TFLOPs: 5.28 | +31: iteration 29340/ 37905 | consumed samples: 7511040 | consumed tokens: 15382609920 | elapsed time per iteration (s): 0.31 | learning rate: 4.174E-05 | global batch size: 256 | lm loss: 2.880356E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 828.603 | TFLOPs: 5.28 | +31: iteration 29350/ 37905 | consumed samples: 7513600 | consumed tokens: 15387852800 | elapsed time per iteration (s): 0.20 | learning rate: 4.169E-05 | global batch size: 256 | lm loss: 2.883706E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.978 | TFLOPs: 7.98 | +31: iteration 29360/ 37905 | consumed samples: 7516160 | consumed tokens: 15393095680 | elapsed time per iteration (s): 0.25 | learning rate: 4.164E-05 | global batch size: 256 | lm loss: 2.920616E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.899 | TFLOPs: 6.62 | +31: iteration 29370/ 37905 | consumed samples: 7518720 | consumed tokens: 15398338560 | elapsed time per iteration (s): 0.21 | learning rate: 4.159E-05 | global batch size: 256 | lm loss: 2.900664E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.161 | TFLOPs: 7.76 | +31: iteration 29380/ 37905 | consumed samples: 7521280 | consumed tokens: 15403581440 | elapsed time per iteration (s): 0.24 | learning rate: 4.155E-05 | global batch size: 256 | lm loss: 2.928676E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.838 | TFLOPs: 6.70 | +31: iteration 29390/ 37905 | consumed samples: 7523840 | consumed tokens: 15408824320 | elapsed time per iteration (s): 0.24 | learning rate: 4.150E-05 | global batch size: 256 | lm loss: 2.906729E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.388 | TFLOPs: 6.80 | +31: iteration 29400/ 37905 | consumed samples: 7526400 | consumed tokens: 15414067200 | elapsed time per iteration (s): 0.22 | learning rate: 4.145E-05 | global batch size: 256 | lm loss: 2.935272E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.416 | TFLOPs: 7.49 | +31: iteration 29410/ 37905 | consumed samples: 7528960 | consumed tokens: 15419310080 | elapsed time per iteration (s): 0.22 | learning rate: 4.140E-05 | global batch size: 256 | lm loss: 2.856982E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.579 | TFLOPs: 7.38 | +31: iteration 29420/ 37905 | consumed samples: 7531520 | consumed tokens: 15424552960 | elapsed time per iteration (s): 0.22 | learning rate: 4.135E-05 | global batch size: 256 | lm loss: 2.861965E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.641 | TFLOPs: 7.43 | +31: iteration 29430/ 37905 | consumed samples: 7534080 | consumed tokens: 15429795840 | elapsed time per iteration (s): 0.23 | learning rate: 4.130E-05 | global batch size: 256 | lm loss: 2.930687E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.487 | TFLOPs: 7.09 | +31: iteration 29440/ 37905 | consumed samples: 7536640 | consumed tokens: 15435038720 | elapsed time per iteration (s): 0.23 | learning rate: 4.126E-05 | global batch size: 256 | lm loss: 2.912277E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.957 | TFLOPs: 7.22 | +31: iteration 29450/ 37905 | consumed samples: 7539200 | consumed tokens: 15440281600 | elapsed time per iteration (s): 0.22 | learning rate: 4.121E-05 | global batch size: 256 | lm loss: 2.897865E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.672 | TFLOPs: 7.31 | +31: iteration 29460/ 37905 | consumed samples: 7541760 | consumed tokens: 15445524480 | elapsed time per iteration (s): 0.25 | learning rate: 4.116E-05 | global batch size: 256 | lm loss: 2.933866E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1016.332 | TFLOPs: 6.47 | +31: iteration 29470/ 37905 | consumed samples: 7544320 | consumed tokens: 15450767360 | elapsed time per iteration (s): 0.22 | learning rate: 4.111E-05 | global batch size: 256 | lm loss: 2.920528E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.501 | TFLOPs: 7.27 | +31: iteration 29480/ 37905 | consumed samples: 7546880 | consumed tokens: 15456010240 | elapsed time per iteration (s): 0.21 | learning rate: 4.106E-05 | global batch size: 256 | lm loss: 2.925960E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.572 | TFLOPs: 7.60 | +31: iteration 29490/ 37905 | consumed samples: 7549440 | consumed tokens: 15461253120 | elapsed time per iteration (s): 0.23 | learning rate: 4.102E-05 | global batch size: 256 | lm loss: 2.889606E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.133 | TFLOPs: 7.13 | +31: iteration 29500/ 37905 | consumed samples: 7552000 | consumed tokens: 15466496000 | elapsed time per iteration (s): 0.21 | learning rate: 4.097E-05 | global batch size: 256 | lm loss: 2.932515E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.569 | TFLOPs: 7.61 | +31: iteration 29510/ 37905 | consumed samples: 7554560 | consumed tokens: 15471738880 | elapsed time per iteration (s): 0.20 | learning rate: 4.092E-05 | global batch size: 256 | lm loss: 2.924600E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.209 | TFLOPs: 8.01 | +31: iteration 29520/ 37905 | consumed samples: 7557120 | consumed tokens: 15476981760 | elapsed time per iteration (s): 0.22 | learning rate: 4.087E-05 | global batch size: 256 | lm loss: 2.918257E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.575 | TFLOPs: 7.39 | +31: iteration 29530/ 37905 | consumed samples: 7559680 | consumed tokens: 15482224640 | elapsed time per iteration (s): 0.19 | learning rate: 4.083E-05 | global batch size: 256 | lm loss: 2.879909E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.102 | TFLOPs: 8.47 | +31: iteration 29540/ 37905 | consumed samples: 7562240 | consumed tokens: 15487467520 | elapsed time per iteration (s): 0.22 | learning rate: 4.078E-05 | global batch size: 256 | lm loss: 2.923039E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.477 | TFLOPs: 7.45 | +31: iteration 29550/ 37905 | consumed samples: 7564800 | consumed tokens: 15492710400 | elapsed time per iteration (s): 0.22 | learning rate: 4.073E-05 | global batch size: 256 | lm loss: 2.885958E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.508 | TFLOPs: 7.55 | +31: iteration 29560/ 37905 | consumed samples: 7567360 | consumed tokens: 15497953280 | elapsed time per iteration (s): 0.24 | learning rate: 4.068E-05 | global batch size: 256 | lm loss: 2.897743E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.671 | TFLOPs: 6.91 | +31: iteration 29570/ 37905 | consumed samples: 7569920 | consumed tokens: 15503196160 | elapsed time per iteration (s): 0.22 | learning rate: 4.063E-05 | global batch size: 256 | lm loss: 2.902062E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.678 | TFLOPs: 7.37 | +31: iteration 29580/ 37905 | consumed samples: 7572480 | consumed tokens: 15508439040 | elapsed time per iteration (s): 0.20 | learning rate: 4.059E-05 | global batch size: 256 | lm loss: 2.919835E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.457 | TFLOPs: 7.96 | +31: iteration 29590/ 37905 | consumed samples: 7575040 | consumed tokens: 15513681920 | elapsed time per iteration (s): 0.22 | learning rate: 4.054E-05 | global batch size: 256 | lm loss: 2.892892E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1155.506 | TFLOPs: 7.36 | +31: iteration 29600/ 37905 | consumed samples: 7577600 | consumed tokens: 15518924800 | elapsed time per iteration (s): 0.19 | learning rate: 4.049E-05 | global batch size: 256 | lm loss: 2.939738E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.529 | TFLOPs: 8.47 | +31: iteration 29610/ 37905 | consumed samples: 7580160 | consumed tokens: 15524167680 | elapsed time per iteration (s): 0.22 | learning rate: 4.044E-05 | global batch size: 256 | lm loss: 2.878821E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.471 | TFLOPs: 7.53 | +31: iteration 29620/ 37905 | consumed samples: 7582720 | consumed tokens: 15529410560 | elapsed time per iteration (s): 0.21 | learning rate: 4.040E-05 | global batch size: 256 | lm loss: 2.913362E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.411 | TFLOPs: 7.86 | +31: iteration 29630/ 37905 | consumed samples: 7585280 | consumed tokens: 15534653440 | elapsed time per iteration (s): 0.22 | learning rate: 4.035E-05 | global batch size: 256 | lm loss: 2.878106E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.356 | TFLOPs: 7.37 | +31: iteration 29640/ 37905 | consumed samples: 7587840 | consumed tokens: 15539896320 | elapsed time per iteration (s): 0.22 | learning rate: 4.030E-05 | global batch size: 256 | lm loss: 2.912403E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.008 | TFLOPs: 7.51 | +31: iteration 29650/ 37905 | consumed samples: 7590400 | consumed tokens: 15545139200 | elapsed time per iteration (s): 0.21 | learning rate: 4.026E-05 | global batch size: 256 | lm loss: 2.897515E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.316 | TFLOPs: 7.90 | +31: iteration 29660/ 37905 | consumed samples: 7592960 | consumed tokens: 15550382080 | elapsed time per iteration (s): 0.22 | learning rate: 4.021E-05 | global batch size: 256 | lm loss: 2.898961E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.260 | TFLOPs: 7.47 | +31: iteration 29670/ 37905 | consumed samples: 7595520 | consumed tokens: 15555624960 | elapsed time per iteration (s): 0.23 | learning rate: 4.016E-05 | global batch size: 256 | lm loss: 2.904995E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.616 | TFLOPs: 6.94 | +31: iteration 29680/ 37905 | consumed samples: 7598080 | consumed tokens: 15560867840 | elapsed time per iteration (s): 0.21 | learning rate: 4.011E-05 | global batch size: 256 | lm loss: 2.928326E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.620 | TFLOPs: 7.65 | +31: iteration 29690/ 37905 | consumed samples: 7600640 | consumed tokens: 15566110720 | elapsed time per iteration (s): 0.23 | learning rate: 4.007E-05 | global batch size: 256 | lm loss: 2.873372E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.669 | TFLOPs: 7.02 | +31: iteration 29700/ 37905 | consumed samples: 7603200 | consumed tokens: 15571353600 | elapsed time per iteration (s): 0.25 | learning rate: 4.002E-05 | global batch size: 256 | lm loss: 2.894849E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.340 | TFLOPs: 6.50 | +31: iteration 29710/ 37905 | consumed samples: 7605760 | consumed tokens: 15576596480 | elapsed time per iteration (s): 0.21 | learning rate: 3.997E-05 | global batch size: 256 | lm loss: 2.895837E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.373 | TFLOPs: 7.75 | +31: iteration 29720/ 37905 | consumed samples: 7608320 | consumed tokens: 15581839360 | elapsed time per iteration (s): 0.20 | learning rate: 3.993E-05 | global batch size: 256 | lm loss: 2.896857E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.737 | TFLOPs: 8.05 | +31: iteration 29730/ 37905 | consumed samples: 7610880 | consumed tokens: 15587082240 | elapsed time per iteration (s): 0.23 | learning rate: 3.988E-05 | global batch size: 256 | lm loss: 2.925080E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.765 | TFLOPs: 7.18 | +31: iteration 29740/ 37905 | consumed samples: 7613440 | consumed tokens: 15592325120 | elapsed time per iteration (s): 0.21 | learning rate: 3.983E-05 | global batch size: 256 | lm loss: 2.906408E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.313 | TFLOPs: 7.85 | +31: iteration 29750/ 37905 | consumed samples: 7616000 | consumed tokens: 15597568000 | elapsed time per iteration (s): 0.23 | learning rate: 3.979E-05 | global batch size: 256 | lm loss: 2.895399E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.366 | TFLOPs: 7.19 | +31: iteration 29760/ 37905 | consumed samples: 7618560 | consumed tokens: 15602810880 | elapsed time per iteration (s): 0.21 | learning rate: 3.974E-05 | global batch size: 256 | lm loss: 2.882991E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.030 | TFLOPs: 7.86 | +31: iteration 29770/ 37905 | consumed samples: 7621120 | consumed tokens: 15608053760 | elapsed time per iteration (s): 0.21 | learning rate: 3.969E-05 | global batch size: 256 | lm loss: 2.904558E+00 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.102 | TFLOPs: 7.75 | +31: iteration 29780/ 37905 | consumed samples: 7623680 | consumed tokens: 15613296640 | elapsed time per iteration (s): 0.24 | learning rate: 3.965E-05 | global batch size: 256 | lm loss: 2.857849E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.107 | TFLOPs: 6.91 | +31: iteration 29790/ 37905 | consumed samples: 7626240 | consumed tokens: 15618539520 | elapsed time per iteration (s): 0.21 | learning rate: 3.960E-05 | global batch size: 256 | lm loss: 2.906138E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.760 | TFLOPs: 7.74 | +31: iteration 29800/ 37905 | consumed samples: 7628800 | consumed tokens: 15623782400 | elapsed time per iteration (s): 0.23 | learning rate: 3.955E-05 | global batch size: 256 | lm loss: 2.934072E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.255 | TFLOPs: 7.04 | +31: iteration 29810/ 37905 | consumed samples: 7631360 | consumed tokens: 15629025280 | elapsed time per iteration (s): 0.21 | learning rate: 3.951E-05 | global batch size: 256 | lm loss: 2.880895E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.498 | TFLOPs: 7.70 | +31: iteration 29820/ 37905 | consumed samples: 7633920 | consumed tokens: 15634268160 | elapsed time per iteration (s): 0.20 | learning rate: 3.946E-05 | global batch size: 256 | lm loss: 2.885166E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.075 | TFLOPs: 8.08 | +31: iteration 29830/ 37905 | consumed samples: 7636480 | consumed tokens: 15639511040 | elapsed time per iteration (s): 0.21 | learning rate: 3.942E-05 | global batch size: 256 | lm loss: 2.923804E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.998 | TFLOPs: 7.73 | +31: iteration 29840/ 37905 | consumed samples: 7639040 | consumed tokens: 15644753920 | elapsed time per iteration (s): 0.22 | learning rate: 3.937E-05 | global batch size: 256 | lm loss: 2.868386E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.923 | TFLOPs: 7.35 | +31: iteration 29850/ 37905 | consumed samples: 7641600 | consumed tokens: 15649996800 | elapsed time per iteration (s): 0.22 | learning rate: 3.932E-05 | global batch size: 256 | lm loss: 2.863077E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1180.529 | TFLOPs: 7.52 | +31: iteration 29860/ 37905 | consumed samples: 7644160 | consumed tokens: 15655239680 | elapsed time per iteration (s): 0.22 | learning rate: 3.928E-05 | global batch size: 256 | lm loss: 2.891963E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.041 | TFLOPs: 7.28 | +31: iteration 29870/ 37905 | consumed samples: 7646720 | consumed tokens: 15660482560 | elapsed time per iteration (s): 0.24 | learning rate: 3.923E-05 | global batch size: 256 | lm loss: 2.875067E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.579 | TFLOPs: 6.88 | +31: iteration 29880/ 37905 | consumed samples: 7649280 | consumed tokens: 15665725440 | elapsed time per iteration (s): 0.22 | learning rate: 3.918E-05 | global batch size: 256 | lm loss: 2.903180E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.441 | TFLOPs: 7.35 | +31: iteration 29890/ 37905 | consumed samples: 7651840 | consumed tokens: 15670968320 | elapsed time per iteration (s): 0.22 | learning rate: 3.914E-05 | global batch size: 256 | lm loss: 2.904495E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.188 | TFLOPs: 7.29 | +31: iteration 29900/ 37905 | consumed samples: 7654400 | consumed tokens: 15676211200 | elapsed time per iteration (s): 0.22 | learning rate: 3.909E-05 | global batch size: 256 | lm loss: 2.925904E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.390 | TFLOPs: 7.35 | +31: iteration 29910/ 37905 | consumed samples: 7656960 | consumed tokens: 15681454080 | elapsed time per iteration (s): 0.22 | learning rate: 3.905E-05 | global batch size: 256 | lm loss: 2.895133E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.220 | TFLOPs: 7.49 | +31: iteration 29920/ 37905 | consumed samples: 7659520 | consumed tokens: 15686696960 | elapsed time per iteration (s): 0.21 | learning rate: 3.900E-05 | global batch size: 256 | lm loss: 2.906659E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.542 | TFLOPs: 7.91 | +31: iteration 29930/ 37905 | consumed samples: 7662080 | consumed tokens: 15691939840 | elapsed time per iteration (s): 0.21 | learning rate: 3.895E-05 | global batch size: 256 | lm loss: 2.883319E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.487 | TFLOPs: 7.80 | +31: iteration 29940/ 37905 | consumed samples: 7664640 | consumed tokens: 15697182720 | elapsed time per iteration (s): 0.22 | learning rate: 3.891E-05 | global batch size: 256 | lm loss: 2.882303E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.120 | TFLOPs: 7.58 | +31: iteration 29950/ 37905 | consumed samples: 7667200 | consumed tokens: 15702425600 | elapsed time per iteration (s): 0.21 | learning rate: 3.886E-05 | global batch size: 256 | lm loss: 2.900377E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.269 | TFLOPs: 7.67 | +31: iteration 29960/ 37905 | consumed samples: 7669760 | consumed tokens: 15707668480 | elapsed time per iteration (s): 0.25 | learning rate: 3.882E-05 | global batch size: 256 | lm loss: 2.899753E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.924 | TFLOPs: 6.65 | +31: iteration 29970/ 37905 | consumed samples: 7672320 | consumed tokens: 15712911360 | elapsed time per iteration (s): 0.23 | learning rate: 3.877E-05 | global batch size: 256 | lm loss: 2.880814E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.930 | TFLOPs: 7.15 | +31: iteration 29980/ 37905 | consumed samples: 7674880 | consumed tokens: 15718154240 | elapsed time per iteration (s): 0.21 | learning rate: 3.873E-05 | global batch size: 256 | lm loss: 2.897961E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.241 | TFLOPs: 7.69 | +31: iteration 29990/ 37905 | consumed samples: 7677440 | consumed tokens: 15723397120 | elapsed time per iteration (s): 0.21 | learning rate: 3.868E-05 | global batch size: 256 | lm loss: 2.909454E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.382 | TFLOPs: 7.73 | + 0: [2022-11-24 16:00:23,407] [INFO] [logging.py:68:log_dist] [Rank 0] step=30000, skipped=0, lr=[3.863540553632879e-05, 3.863540553632879e-05, 3.863540553632879e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 30000/ 37905 | consumed samples: 7680000 | consumed tokens: 15728640000 | elapsed time per iteration (s): 0.22 | learning rate: 3.864E-05 | global batch size: 256 | lm loss: 2.915963E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.362 | TFLOPs: 7.35 | + 0: steps: 30000 loss: 2.8724 iter time (s): 0.224 samples/sec: 1144.751 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 30000 | lm loss value: 2.895459E+00 | lm loss PPL: 1.809180E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 30000 to checkpoints_83m + 0: [2022-11-24 16:00:23,494] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step30000 is begin to save! + 0: [2022-11-24 16:00:23,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,594] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,605] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,626] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,626] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,637] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,659] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,659] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,681] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,692] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:00:23,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:00:23,694] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step30000/mp_rank_00_model_states.pt + 0: [2022-11-24 16:00:23,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:00:23,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:00:23,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:00:23,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:00:23,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:00:23,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-24 16:00:23,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:00:23,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 16:00:23,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-24 16:00:23,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:00:23,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:00:23,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 16:00:23,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 16:00:23,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:00:23,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-24 16:00:23,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:00:23,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 16:00:23,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-24 16:00:23,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-24 16:00:23,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:00:23,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:00:23,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:00:23,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-24 16:00:23,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-24 16:00:23,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-24 16:00:23,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:00:23,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:00:23,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:00:23,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:00:23,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +28: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:00:23,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:00:23,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +10: [2022-11-24 16:00:23,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +15: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:00:23,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-24 16:00:23,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +24: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:00:23,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 16:00:23,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-24 16:00:23,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:00:23,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:00:23,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:00:23,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:00:23,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:00:23,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:00:23,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:00:23,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:00:23,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-24 16:00:23,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 16:00:23,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:00:23,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:00:23,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-24 16:00:23,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:00:23,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:00:23,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 16:00:23,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-24 16:00:23,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:00:23,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-24 16:00:23,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:00:23,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-24 16:00:23,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:00:23,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-24 16:00:23,792] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,792] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:00:23,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:00:23,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +22: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,793] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:00:23,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,794] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:00:23,795] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:00:23,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 16:00:23,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-24 16:00:23,796] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:00:23,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:00:23,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 16:00:23,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-24 16:00:23,797] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:00:23,798] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,798] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:00:23,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,799] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,800] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,800] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:00:23,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:00:23,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,801] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 16:00:23,801] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:00:23,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,802] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-24 16:00:23,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-24 16:00:23,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:00:23,803] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,803] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:00:23,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-24 16:00:23,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:00:23,804] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,804] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:00:23,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,805] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:00:23,805] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-24 16:00:23,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:00:23,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +15: [2022-11-24 16:00:23,806] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:00:23,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:00:23,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,807] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,808] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 16:00:23,808] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:00:23,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,809] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 16:00:23,809] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:00:23,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,810] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:00:23,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +28: [2022-11-24 16:00:23,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:00:23,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,811] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,811] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:00:23,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:00:23,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:00:23,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-24 16:00:23,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:00:23,812] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,812] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:00:23,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-24 16:00:23,813] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:00:23,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,814] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,814] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-24 16:00:23,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 16:00:23,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 1: [2022-11-24 16:00:23,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,815] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:00:23,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,816] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:00:23,816] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,816] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:00:23,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:00:23,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +27: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,817] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:00:23,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +23: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:00:23,818] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,818] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 16:00:23,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,819] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 16:00:23,819] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:00:23,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:00:23,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:00:23,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:00:23,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-24 16:00:23,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:00:23,820] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 16:00:23,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-24 16:00:23,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,821] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 16:00:23,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-24 16:00:23,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +24: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +14: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +17: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 6: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +17: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 9: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +29: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +25: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +30: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,822] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:00:23,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 8: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 5: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +22: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +26: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +26: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +15: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +18: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +10: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +20: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +24: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +23: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +28: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +27: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +19: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +15: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +24: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +18: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +31: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +10: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +19: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 2: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +13: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +29: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +31: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 3: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +13: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 4: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +12: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 7: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +11: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +12: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +11: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +21: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! +16: [2022-11-24 16:00:23,823] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step30000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 16:00:23,823] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step30000 is ready now! + 0: successfully saved checkpoint at iteration 30000 to checkpoints_83m +31: time (ms) | save-checkpoint: 334.21 +31: iteration 30010/ 37905 | consumed samples: 7682560 | consumed tokens: 15733882880 | elapsed time per iteration (s): 0.29 | learning rate: 3.859E-05 | global batch size: 256 | lm loss: 2.893217E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 896.532 | TFLOPs: 5.71 | +31: iteration 30020/ 37905 | consumed samples: 7685120 | consumed tokens: 15739125760 | elapsed time per iteration (s): 0.24 | learning rate: 3.854E-05 | global batch size: 256 | lm loss: 2.917126E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.158 | TFLOPs: 6.82 | +31: iteration 30030/ 37905 | consumed samples: 7687680 | consumed tokens: 15744368640 | elapsed time per iteration (s): 0.24 | learning rate: 3.850E-05 | global batch size: 256 | lm loss: 2.912506E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.156 | TFLOPs: 6.78 | +31: iteration 30040/ 37905 | consumed samples: 7690240 | consumed tokens: 15749611520 | elapsed time per iteration (s): 0.24 | learning rate: 3.845E-05 | global batch size: 256 | lm loss: 2.885133E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.013 | TFLOPs: 6.77 | +31: iteration 30050/ 37905 | consumed samples: 7692800 | consumed tokens: 15754854400 | elapsed time per iteration (s): 0.23 | learning rate: 3.841E-05 | global batch size: 256 | lm loss: 2.914225E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.219 | TFLOPs: 7.23 | +31: iteration 30060/ 37905 | consumed samples: 7695360 | consumed tokens: 15760097280 | elapsed time per iteration (s): 0.20 | learning rate: 3.836E-05 | global batch size: 256 | lm loss: 2.910323E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.175 | TFLOPs: 8.24 | +31: iteration 30070/ 37905 | consumed samples: 7697920 | consumed tokens: 15765340160 | elapsed time per iteration (s): 0.24 | learning rate: 3.832E-05 | global batch size: 256 | lm loss: 2.911719E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.929 | TFLOPs: 6.90 | +31: iteration 30080/ 37905 | consumed samples: 7700480 | consumed tokens: 15770583040 | elapsed time per iteration (s): 0.20 | learning rate: 3.827E-05 | global batch size: 256 | lm loss: 2.920288E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.396 | TFLOPs: 8.15 | +31: iteration 30090/ 37905 | consumed samples: 7703040 | consumed tokens: 15775825920 | elapsed time per iteration (s): 0.23 | learning rate: 3.823E-05 | global batch size: 256 | lm loss: 2.891834E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.920 | TFLOPs: 7.09 | +31: iteration 30100/ 37905 | consumed samples: 7705600 | consumed tokens: 15781068800 | elapsed time per iteration (s): 0.26 | learning rate: 3.818E-05 | global batch size: 256 | lm loss: 2.879018E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 992.742 | TFLOPs: 6.32 | +31: iteration 30110/ 37905 | consumed samples: 7708160 | consumed tokens: 15786311680 | elapsed time per iteration (s): 0.22 | learning rate: 3.814E-05 | global batch size: 256 | lm loss: 2.916256E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.744 | TFLOPs: 7.32 | +31: iteration 30120/ 37905 | consumed samples: 7710720 | consumed tokens: 15791554560 | elapsed time per iteration (s): 0.24 | learning rate: 3.809E-05 | global batch size: 256 | lm loss: 2.891250E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.765 | TFLOPs: 6.82 | +31: iteration 30130/ 37905 | consumed samples: 7713280 | consumed tokens: 15796797440 | elapsed time per iteration (s): 0.21 | learning rate: 3.805E-05 | global batch size: 256 | lm loss: 2.903831E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1214.340 | TFLOPs: 7.73 | +31: iteration 30140/ 37905 | consumed samples: 7715840 | consumed tokens: 15802040320 | elapsed time per iteration (s): 0.26 | learning rate: 3.800E-05 | global batch size: 256 | lm loss: 2.911355E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.809 | TFLOPs: 6.35 | +31: iteration 30150/ 37905 | consumed samples: 7718400 | consumed tokens: 15807283200 | elapsed time per iteration (s): 0.24 | learning rate: 3.796E-05 | global batch size: 256 | lm loss: 2.903367E+00 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.928 | TFLOPs: 6.71 | +31: iteration 30160/ 37905 | consumed samples: 7720960 | consumed tokens: 15812526080 | elapsed time per iteration (s): 0.21 | learning rate: 3.791E-05 | global batch size: 256 | lm loss: 2.911747E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.556 | TFLOPs: 7.94 | +31: iteration 30170/ 37905 | consumed samples: 7723520 | consumed tokens: 15817768960 | elapsed time per iteration (s): 0.22 | learning rate: 3.787E-05 | global batch size: 256 | lm loss: 2.892901E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.531 | TFLOPs: 7.39 | +31: iteration 30180/ 37905 | consumed samples: 7726080 | consumed tokens: 15823011840 | elapsed time per iteration (s): 0.22 | learning rate: 3.783E-05 | global batch size: 256 | lm loss: 2.903122E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.816 | TFLOPs: 7.58 | +31: iteration 30190/ 37905 | consumed samples: 7728640 | consumed tokens: 15828254720 | elapsed time per iteration (s): 0.21 | learning rate: 3.778E-05 | global batch size: 256 | lm loss: 2.882074E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.976 | TFLOPs: 7.78 | +31: iteration 30200/ 37905 | consumed samples: 7731200 | consumed tokens: 15833497600 | elapsed time per iteration (s): 0.21 | learning rate: 3.774E-05 | global batch size: 256 | lm loss: 2.914780E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.810 | TFLOPs: 7.64 | +31: iteration 30210/ 37905 | consumed samples: 7733760 | consumed tokens: 15838740480 | elapsed time per iteration (s): 0.21 | learning rate: 3.769E-05 | global batch size: 256 | lm loss: 2.883627E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.678 | TFLOPs: 7.86 | +31: iteration 30220/ 37905 | consumed samples: 7736320 | consumed tokens: 15843983360 | elapsed time per iteration (s): 0.22 | learning rate: 3.765E-05 | global batch size: 256 | lm loss: 2.901053E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.087 | TFLOPs: 7.37 | +31: iteration 30230/ 37905 | consumed samples: 7738880 | consumed tokens: 15849226240 | elapsed time per iteration (s): 0.23 | learning rate: 3.760E-05 | global batch size: 256 | lm loss: 2.893044E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.986 | TFLOPs: 7.05 | +31: iteration 30240/ 37905 | consumed samples: 7741440 | consumed tokens: 15854469120 | elapsed time per iteration (s): 0.25 | learning rate: 3.756E-05 | global batch size: 256 | lm loss: 2.869745E+00 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.761 | TFLOPs: 6.64 | +31: iteration 30250/ 37905 | consumed samples: 7744000 | consumed tokens: 15859712000 | elapsed time per iteration (s): 0.24 | learning rate: 3.751E-05 | global batch size: 256 | lm loss: 2.930289E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.877 | TFLOPs: 6.66 | +31: iteration 30260/ 37905 | consumed samples: 7746560 | consumed tokens: 15864954880 | elapsed time per iteration (s): 0.20 | learning rate: 3.747E-05 | global batch size: 256 | lm loss: 2.927425E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.370 | TFLOPs: 8.06 | +31: iteration 30270/ 37905 | consumed samples: 7749120 | consumed tokens: 15870197760 | elapsed time per iteration (s): 0.21 | learning rate: 3.743E-05 | global batch size: 256 | lm loss: 2.912456E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.700 | TFLOPs: 7.79 | +31: iteration 30280/ 37905 | consumed samples: 7751680 | consumed tokens: 15875440640 | elapsed time per iteration (s): 0.21 | learning rate: 3.738E-05 | global batch size: 256 | lm loss: 2.921624E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.717 | TFLOPs: 7.76 | +31: iteration 30290/ 37905 | consumed samples: 7754240 | consumed tokens: 15880683520 | elapsed time per iteration (s): 0.22 | learning rate: 3.734E-05 | global batch size: 256 | lm loss: 2.926559E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.896 | TFLOPs: 7.51 | +31: iteration 30300/ 37905 | consumed samples: 7756800 | consumed tokens: 15885926400 | elapsed time per iteration (s): 0.23 | learning rate: 3.729E-05 | global batch size: 256 | lm loss: 2.878019E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.311 | TFLOPs: 7.03 | +31: iteration 30310/ 37905 | consumed samples: 7759360 | consumed tokens: 15891169280 | elapsed time per iteration (s): 0.21 | learning rate: 3.725E-05 | global batch size: 256 | lm loss: 2.873811E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.989 | TFLOPs: 7.88 | +31: iteration 30320/ 37905 | consumed samples: 7761920 | consumed tokens: 15896412160 | elapsed time per iteration (s): 0.21 | learning rate: 3.721E-05 | global batch size: 256 | lm loss: 2.927212E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.199 | TFLOPs: 7.62 | +31: iteration 30330/ 37905 | consumed samples: 7764480 | consumed tokens: 15901655040 | elapsed time per iteration (s): 0.22 | learning rate: 3.716E-05 | global batch size: 256 | lm loss: 2.892581E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.051 | TFLOPs: 7.52 | +31: iteration 30340/ 37905 | consumed samples: 7767040 | consumed tokens: 15906897920 | elapsed time per iteration (s): 0.22 | learning rate: 3.712E-05 | global batch size: 256 | lm loss: 2.903815E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.062 | TFLOPs: 7.45 | +31: iteration 30350/ 37905 | consumed samples: 7769600 | consumed tokens: 15912140800 | elapsed time per iteration (s): 0.22 | learning rate: 3.707E-05 | global batch size: 256 | lm loss: 2.875836E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.829 | TFLOPs: 7.37 | +31: iteration 30360/ 37905 | consumed samples: 7772160 | consumed tokens: 15917383680 | elapsed time per iteration (s): 0.20 | learning rate: 3.703E-05 | global batch size: 256 | lm loss: 2.920061E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1276.937 | TFLOPs: 8.13 | +31: iteration 30370/ 37905 | consumed samples: 7774720 | consumed tokens: 15922626560 | elapsed time per iteration (s): 0.20 | learning rate: 3.699E-05 | global batch size: 256 | lm loss: 2.903392E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.723 | TFLOPs: 8.11 | +31: iteration 30380/ 37905 | consumed samples: 7777280 | consumed tokens: 15927869440 | elapsed time per iteration (s): 0.23 | learning rate: 3.694E-05 | global batch size: 256 | lm loss: 2.928196E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.977 | TFLOPs: 7.16 | +31: iteration 30390/ 37905 | consumed samples: 7779840 | consumed tokens: 15933112320 | elapsed time per iteration (s): 0.21 | learning rate: 3.690E-05 | global batch size: 256 | lm loss: 2.928998E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.155 | TFLOPs: 7.75 | +31: iteration 30400/ 37905 | consumed samples: 7782400 | consumed tokens: 15938355200 | elapsed time per iteration (s): 0.21 | learning rate: 3.686E-05 | global batch size: 256 | lm loss: 2.909464E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.557 | TFLOPs: 7.79 | +31: iteration 30410/ 37905 | consumed samples: 7784960 | consumed tokens: 15943598080 | elapsed time per iteration (s): 0.23 | learning rate: 3.681E-05 | global batch size: 256 | lm loss: 2.882039E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.806 | TFLOPs: 7.06 | +31: iteration 30420/ 37905 | consumed samples: 7787520 | consumed tokens: 15948840960 | elapsed time per iteration (s): 0.19 | learning rate: 3.677E-05 | global batch size: 256 | lm loss: 2.883435E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.607 | TFLOPs: 8.58 | +31: iteration 30430/ 37905 | consumed samples: 7790080 | consumed tokens: 15954083840 | elapsed time per iteration (s): 0.24 | learning rate: 3.673E-05 | global batch size: 256 | lm loss: 2.886441E+00 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.646 | TFLOPs: 6.93 | +31: iteration 30440/ 37905 | consumed samples: 7792640 | consumed tokens: 15959326720 | elapsed time per iteration (s): 0.25 | learning rate: 3.668E-05 | global batch size: 256 | lm loss: 2.922501E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.737 | TFLOPs: 6.56 | +31: iteration 30450/ 37905 | consumed samples: 7795200 | consumed tokens: 15964569600 | elapsed time per iteration (s): 0.22 | learning rate: 3.664E-05 | global batch size: 256 | lm loss: 2.877044E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.112 | TFLOPs: 7.41 | +31: iteration 30460/ 37905 | consumed samples: 7797760 | consumed tokens: 15969812480 | elapsed time per iteration (s): 0.21 | learning rate: 3.660E-05 | global batch size: 256 | lm loss: 2.879162E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.072 | TFLOPs: 7.94 | +31: iteration 30470/ 37905 | consumed samples: 7800320 | consumed tokens: 15975055360 | elapsed time per iteration (s): 0.23 | learning rate: 3.655E-05 | global batch size: 256 | lm loss: 2.918137E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.729 | TFLOPs: 7.00 | +31: iteration 30480/ 37905 | consumed samples: 7802880 | consumed tokens: 15980298240 | elapsed time per iteration (s): 0.21 | learning rate: 3.651E-05 | global batch size: 256 | lm loss: 2.891735E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.260 | TFLOPs: 7.85 | +31: iteration 30490/ 37905 | consumed samples: 7805440 | consumed tokens: 15985541120 | elapsed time per iteration (s): 0.21 | learning rate: 3.647E-05 | global batch size: 256 | lm loss: 2.907999E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.047 | TFLOPs: 7.91 | +31: iteration 30500/ 37905 | consumed samples: 7808000 | consumed tokens: 15990784000 | elapsed time per iteration (s): 0.21 | learning rate: 3.642E-05 | global batch size: 256 | lm loss: 2.877038E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.693 | TFLOPs: 7.75 | +31: iteration 30510/ 37905 | consumed samples: 7810560 | consumed tokens: 15996026880 | elapsed time per iteration (s): 0.23 | learning rate: 3.638E-05 | global batch size: 256 | lm loss: 2.917196E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.642 | TFLOPs: 7.22 | +31: iteration 30520/ 37905 | consumed samples: 7813120 | consumed tokens: 16001269760 | elapsed time per iteration (s): 0.22 | learning rate: 3.634E-05 | global batch size: 256 | lm loss: 2.898950E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.258 | TFLOPs: 7.41 | +31: iteration 30530/ 37905 | consumed samples: 7815680 | consumed tokens: 16006512640 | elapsed time per iteration (s): 0.20 | learning rate: 3.630E-05 | global batch size: 256 | lm loss: 2.886916E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.248 | TFLOPs: 8.10 | +31: iteration 30540/ 37905 | consumed samples: 7818240 | consumed tokens: 16011755520 | elapsed time per iteration (s): 0.23 | learning rate: 3.625E-05 | global batch size: 256 | lm loss: 2.867811E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.972 | TFLOPs: 7.23 | +31: iteration 30550/ 37905 | consumed samples: 7820800 | consumed tokens: 16016998400 | elapsed time per iteration (s): 0.24 | learning rate: 3.621E-05 | global batch size: 256 | lm loss: 2.923409E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.048 | TFLOPs: 6.76 | +31: iteration 30560/ 37905 | consumed samples: 7823360 | consumed tokens: 16022241280 | elapsed time per iteration (s): 0.24 | learning rate: 3.617E-05 | global batch size: 256 | lm loss: 2.920661E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.665 | TFLOPs: 6.74 | +31: iteration 30570/ 37905 | consumed samples: 7825920 | consumed tokens: 16027484160 | elapsed time per iteration (s): 0.22 | learning rate: 3.613E-05 | global batch size: 256 | lm loss: 2.938688E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.826 | TFLOPs: 7.31 | +31: iteration 30580/ 37905 | consumed samples: 7828480 | consumed tokens: 16032727040 | elapsed time per iteration (s): 0.24 | learning rate: 3.608E-05 | global batch size: 256 | lm loss: 2.855557E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.897 | TFLOPs: 6.72 | +31: iteration 30590/ 37905 | consumed samples: 7831040 | consumed tokens: 16037969920 | elapsed time per iteration (s): 0.21 | learning rate: 3.604E-05 | global batch size: 256 | lm loss: 2.913626E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1233.253 | TFLOPs: 7.85 | +31: iteration 30600/ 37905 | consumed samples: 7833600 | consumed tokens: 16043212800 | elapsed time per iteration (s): 0.21 | learning rate: 3.600E-05 | global batch size: 256 | lm loss: 2.906011E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1228.008 | TFLOPs: 7.82 | +31: iteration 30610/ 37905 | consumed samples: 7836160 | consumed tokens: 16048455680 | elapsed time per iteration (s): 0.21 | learning rate: 3.596E-05 | global batch size: 256 | lm loss: 2.896308E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.001 | TFLOPs: 7.80 | +31: iteration 30620/ 37905 | consumed samples: 7838720 | consumed tokens: 16053698560 | elapsed time per iteration (s): 0.24 | learning rate: 3.591E-05 | global batch size: 256 | lm loss: 2.901463E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.854 | TFLOPs: 6.73 | +31: iteration 30630/ 37905 | consumed samples: 7841280 | consumed tokens: 16058941440 | elapsed time per iteration (s): 0.22 | learning rate: 3.587E-05 | global batch size: 256 | lm loss: 2.873327E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.077 | TFLOPs: 7.46 | +31: iteration 30640/ 37905 | consumed samples: 7843840 | consumed tokens: 16064184320 | elapsed time per iteration (s): 0.20 | learning rate: 3.583E-05 | global batch size: 256 | lm loss: 2.870794E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.614 | TFLOPs: 8.18 | +31: iteration 30650/ 37905 | consumed samples: 7846400 | consumed tokens: 16069427200 | elapsed time per iteration (s): 0.25 | learning rate: 3.579E-05 | global batch size: 256 | lm loss: 2.906245E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.480 | TFLOPs: 6.61 | +31: iteration 30660/ 37905 | consumed samples: 7848960 | consumed tokens: 16074670080 | elapsed time per iteration (s): 0.21 | learning rate: 3.574E-05 | global batch size: 256 | lm loss: 2.903086E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.110 | TFLOPs: 7.88 | +31: iteration 30670/ 37905 | consumed samples: 7851520 | consumed tokens: 16079912960 | elapsed time per iteration (s): 0.21 | learning rate: 3.570E-05 | global batch size: 256 | lm loss: 2.915691E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.424 | TFLOPs: 7.64 | +31: iteration 30680/ 37905 | consumed samples: 7854080 | consumed tokens: 16085155840 | elapsed time per iteration (s): 0.21 | learning rate: 3.566E-05 | global batch size: 256 | lm loss: 2.950084E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.307 | TFLOPs: 7.66 | +31: iteration 30690/ 37905 | consumed samples: 7856640 | consumed tokens: 16090398720 | elapsed time per iteration (s): 0.26 | learning rate: 3.562E-05 | global batch size: 256 | lm loss: 2.918705E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.319 | TFLOPs: 6.35 | +31: iteration 30700/ 37905 | consumed samples: 7859200 | consumed tokens: 16095641600 | elapsed time per iteration (s): 0.22 | learning rate: 3.558E-05 | global batch size: 256 | lm loss: 2.922537E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.292 | TFLOPs: 7.41 | +31: iteration 30710/ 37905 | consumed samples: 7861760 | consumed tokens: 16100884480 | elapsed time per iteration (s): 0.22 | learning rate: 3.553E-05 | global batch size: 256 | lm loss: 2.900210E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.306 | TFLOPs: 7.39 | +31: iteration 30720/ 37905 | consumed samples: 7864320 | consumed tokens: 16106127360 | elapsed time per iteration (s): 0.22 | learning rate: 3.549E-05 | global batch size: 256 | lm loss: 2.895266E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.969 | TFLOPs: 7.39 | +31: iteration 30730/ 37905 | consumed samples: 7866880 | consumed tokens: 16111370240 | elapsed time per iteration (s): 0.22 | learning rate: 3.545E-05 | global batch size: 256 | lm loss: 2.905839E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.415 | TFLOPs: 7.47 | +31: iteration 30740/ 37905 | consumed samples: 7869440 | consumed tokens: 16116613120 | elapsed time per iteration (s): 0.24 | learning rate: 3.541E-05 | global batch size: 256 | lm loss: 2.877646E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.780 | TFLOPs: 6.88 | +31: iteration 30750/ 37905 | consumed samples: 7872000 | consumed tokens: 16121856000 | elapsed time per iteration (s): 0.21 | learning rate: 3.537E-05 | global batch size: 256 | lm loss: 2.899403E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.195 | TFLOPs: 7.62 | +31: iteration 30760/ 37905 | consumed samples: 7874560 | consumed tokens: 16127098880 | elapsed time per iteration (s): 0.22 | learning rate: 3.533E-05 | global batch size: 256 | lm loss: 2.893998E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1162.429 | TFLOPs: 7.40 | +31: iteration 30770/ 37905 | consumed samples: 7877120 | consumed tokens: 16132341760 | elapsed time per iteration (s): 0.21 | learning rate: 3.528E-05 | global batch size: 256 | lm loss: 2.879845E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.821 | TFLOPs: 7.88 | +31: iteration 30780/ 37905 | consumed samples: 7879680 | consumed tokens: 16137584640 | elapsed time per iteration (s): 0.24 | learning rate: 3.524E-05 | global batch size: 256 | lm loss: 2.903038E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1087.600 | TFLOPs: 6.93 | +31: iteration 30790/ 37905 | consumed samples: 7882240 | consumed tokens: 16142827520 | elapsed time per iteration (s): 0.23 | learning rate: 3.520E-05 | global batch size: 256 | lm loss: 2.846702E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.971 | TFLOPs: 7.11 | +31: iteration 30800/ 37905 | consumed samples: 7884800 | consumed tokens: 16148070400 | elapsed time per iteration (s): 0.24 | learning rate: 3.516E-05 | global batch size: 256 | lm loss: 2.905315E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.580 | TFLOPs: 6.88 | +31: iteration 30810/ 37905 | consumed samples: 7887360 | consumed tokens: 16153313280 | elapsed time per iteration (s): 0.24 | learning rate: 3.512E-05 | global batch size: 256 | lm loss: 2.876912E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.811 | TFLOPs: 6.92 | +31: iteration 30820/ 37905 | consumed samples: 7889920 | consumed tokens: 16158556160 | elapsed time per iteration (s): 0.24 | learning rate: 3.508E-05 | global batch size: 256 | lm loss: 2.893233E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.079 | TFLOPs: 6.67 | +31: iteration 30830/ 37905 | consumed samples: 7892480 | consumed tokens: 16163799040 | elapsed time per iteration (s): 0.24 | learning rate: 3.503E-05 | global batch size: 256 | lm loss: 2.880219E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.057 | TFLOPs: 6.83 | +31: iteration 30840/ 37905 | consumed samples: 7895040 | consumed tokens: 16169041920 | elapsed time per iteration (s): 0.22 | learning rate: 3.499E-05 | global batch size: 256 | lm loss: 2.921715E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.777 | TFLOPs: 7.32 | +31: iteration 30850/ 37905 | consumed samples: 7897600 | consumed tokens: 16174284800 | elapsed time per iteration (s): 0.24 | learning rate: 3.495E-05 | global batch size: 256 | lm loss: 2.904558E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.737 | TFLOPs: 6.78 | +31: iteration 30860/ 37905 | consumed samples: 7900160 | consumed tokens: 16179527680 | elapsed time per iteration (s): 0.23 | learning rate: 3.491E-05 | global batch size: 256 | lm loss: 2.892052E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.198 | TFLOPs: 7.13 | +31: iteration 30870/ 37905 | consumed samples: 7902720 | consumed tokens: 16184770560 | elapsed time per iteration (s): 0.22 | learning rate: 3.487E-05 | global batch size: 256 | lm loss: 2.915576E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.160 | TFLOPs: 7.29 | +31: iteration 30880/ 37905 | consumed samples: 7905280 | consumed tokens: 16190013440 | elapsed time per iteration (s): 0.26 | learning rate: 3.483E-05 | global batch size: 256 | lm loss: 2.872031E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 977.170 | TFLOPs: 6.22 | +31: iteration 30890/ 37905 | consumed samples: 7907840 | consumed tokens: 16195256320 | elapsed time per iteration (s): 0.24 | learning rate: 3.479E-05 | global batch size: 256 | lm loss: 2.897037E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.260 | TFLOPs: 6.75 | +31: iteration 30900/ 37905 | consumed samples: 7910400 | consumed tokens: 16200499200 | elapsed time per iteration (s): 0.23 | learning rate: 3.475E-05 | global batch size: 256 | lm loss: 2.878967E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.675 | TFLOPs: 7.13 | +31: iteration 30910/ 37905 | consumed samples: 7912960 | consumed tokens: 16205742080 | elapsed time per iteration (s): 0.26 | learning rate: 3.471E-05 | global batch size: 256 | lm loss: 2.883028E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 979.686 | TFLOPs: 6.24 | +31: iteration 30920/ 37905 | consumed samples: 7915520 | consumed tokens: 16210984960 | elapsed time per iteration (s): 0.22 | learning rate: 3.467E-05 | global batch size: 256 | lm loss: 2.907767E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.251 | TFLOPs: 7.45 | +31: iteration 30930/ 37905 | consumed samples: 7918080 | consumed tokens: 16216227840 | elapsed time per iteration (s): 0.24 | learning rate: 3.462E-05 | global batch size: 256 | lm loss: 2.891998E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.755 | TFLOPs: 6.89 | +31: iteration 30940/ 37905 | consumed samples: 7920640 | consumed tokens: 16221470720 | elapsed time per iteration (s): 0.21 | learning rate: 3.458E-05 | global batch size: 256 | lm loss: 2.905969E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.719 | TFLOPs: 7.62 | +31: iteration 30950/ 37905 | consumed samples: 7923200 | consumed tokens: 16226713600 | elapsed time per iteration (s): 0.22 | learning rate: 3.454E-05 | global batch size: 256 | lm loss: 2.873914E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.962 | TFLOPs: 7.29 | +31: iteration 30960/ 37905 | consumed samples: 7925760 | consumed tokens: 16231956480 | elapsed time per iteration (s): 0.22 | learning rate: 3.450E-05 | global batch size: 256 | lm loss: 2.920124E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.986 | TFLOPs: 7.50 | +31: iteration 30970/ 37905 | consumed samples: 7928320 | consumed tokens: 16237199360 | elapsed time per iteration (s): 0.22 | learning rate: 3.446E-05 | global batch size: 256 | lm loss: 2.903068E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.284 | TFLOPs: 7.32 | +31: iteration 30980/ 37905 | consumed samples: 7930880 | consumed tokens: 16242442240 | elapsed time per iteration (s): 0.23 | learning rate: 3.442E-05 | global batch size: 256 | lm loss: 2.854454E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.787 | TFLOPs: 7.07 | +31: iteration 30990/ 37905 | consumed samples: 7933440 | consumed tokens: 16247685120 | elapsed time per iteration (s): 0.22 | learning rate: 3.438E-05 | global batch size: 256 | lm loss: 2.890978E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.795 | TFLOPs: 7.40 | +31: iteration 31000/ 37905 | consumed samples: 7936000 | consumed tokens: 16252928000 | elapsed time per iteration (s): 0.21 | learning rate: 3.434E-05 | global batch size: 256 | lm loss: 2.908920E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.675 | TFLOPs: 7.61 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 31000 | lm loss value: 2.732774E+00 | lm loss PPL: 1.537548E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 31000 to checkpoints_83m + 0: [2022-11-24 16:04:08,029] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step31000 is begin to save! + 0: [2022-11-24 16:04:08,037] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,109] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,122] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,133] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,144] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,166] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,166] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,177] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,177] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,187] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,188] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,199] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,209] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,220] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:04:08,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:04:08,222] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step31000/mp_rank_00_model_states.pt + 0: [2022-11-24 16:04:08,222] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:04:08,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:04:08,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step31000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:04:08,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:04:08,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +14: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:04:08,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:04:08,296] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +12: [2022-11-24 16:04:08,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,297] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +10: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,297] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 2: [2022-11-24 16:04:08,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,298] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,298] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,298] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:04:08,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 1: [2022-11-24 16:04:08,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,299] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:04:08,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +19: [2022-11-24 16:04:08,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +17: [2022-11-24 16:04:08,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,300] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:04:08,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,301] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:04:08,301] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,301] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +20: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 4: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +30: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +12: [2022-11-24 16:04:08,302] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +10: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:04:08,303] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +26: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 2: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:04:08,304] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,304] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 1: [2022-11-24 16:04:08,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +28: [2022-11-24 16:04:08,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:04:08,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:04:08,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:04:08,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,305] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +17: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +23: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,306] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +20: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 3: [2022-11-24 16:04:08,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:04:08,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:04:08,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:04:08,307] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 4: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:04:08,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +14: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:04:08,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,308] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:04:08,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +10: [2022-11-24 16:04:08,309] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,309] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +10: [2022-11-24 16:04:08,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:04:08,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 2: [2022-11-24 16:04:08,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,310] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:04:08,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +26: [2022-11-24 16:04:08,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 16:04:08,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:04:08,311] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 1: [2022-11-24 16:04:08,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:04:08,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 16:04:08,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:04:08,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,312] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:04:08,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:04:08,312] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +19: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +23: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,313] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +17: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 3: [2022-11-24 16:04:08,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,314] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:04:08,314] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,314] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:04:08,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +20: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 4: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +14: [2022-11-24 16:04:08,315] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:04:08,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:04:08,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:04:08,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +10: [2022-11-24 16:04:08,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,316] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 16:04:08,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 2: [2022-11-24 16:04:08,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:04:08,317] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,317] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +26: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 1: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:04:08,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,318] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +28: [2022-11-24 16:04:08,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:04:08,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +19: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:04:08,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:04:08,319] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +17: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +23: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,320] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 3: [2022-11-24 16:04:08,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:04:08,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,321] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +20: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:04:08,321] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,322] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:04:08,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +14: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +12: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,323] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 16:04:08,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +10: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:04:08,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:04:08,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 2: [2022-11-24 16:04:08,324] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,324] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +26: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:04:08,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 1: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,325] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:04:08,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +19: [2022-11-24 16:04:08,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,326] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +17: [2022-11-24 16:04:08,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:04:08,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +23: [2022-11-24 16:04:08,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +23: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,327] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 4: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +20: [2022-11-24 16:04:08,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:04:08,328] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:04:08,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +14: [2022-11-24 16:04:08,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,329] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 16:04:08,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:04:08,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +10: [2022-11-24 16:04:08,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +10: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:04:08,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 2: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,330] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,331] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:04:08,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,332] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:04:08,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +19: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:04:08,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +17: [2022-11-24 16:04:08,333] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:04:08,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 3: [2022-11-24 16:04:08,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,334] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:04:08,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +20: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:04:08,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:04:08,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 4: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,335] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +14: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +10: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,336] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:04:08,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:04:08,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:04:08,337] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:04:08,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:04:08,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 2: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +26: [2022-11-24 16:04:08,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:04:08,338] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:04:08,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 16:04:08,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 1: [2022-11-24 16:04:08,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,339] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:04:08,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +19: [2022-11-24 16:04:08,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +17: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +19: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +19: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 4: [2022-11-24 16:04:08,340] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +11: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +14: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +14: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 6: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +20: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +26: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +26: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +17: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +11: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 8: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +20: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +26: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 9: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +27: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +10: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +30: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 7: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +12: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 5: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +27: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +10: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +30: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +22: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +15: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +24: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +23: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +29: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +22: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +23: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +28: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +15: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +24: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +21: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +23: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +12: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 3: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +18: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +29: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +25: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +25: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 1: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +18: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +28: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +16: [2022-11-24 16:04:08,341] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 16:04:08,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +13: [2022-11-24 16:04:08,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 16:04:08,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:04:08,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:04:08,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,342] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step31000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 16:04:08,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! +31: [2022-11-24 16:04:08,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step31000 is ready now! + 0: successfully saved checkpoint at iteration 31000 to checkpoints_83m +31: time (ms) | save-checkpoint: 316.87 +31: iteration 31010/ 37905 | consumed samples: 7938560 | consumed tokens: 16258170880 | elapsed time per iteration (s): 0.31 | learning rate: 3.430E-05 | global batch size: 256 | lm loss: 2.912459E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 837.315 | TFLOPs: 5.33 | +31: iteration 31020/ 37905 | consumed samples: 7941120 | consumed tokens: 16263413760 | elapsed time per iteration (s): 0.21 | learning rate: 3.426E-05 | global batch size: 256 | lm loss: 2.963776E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1242.887 | TFLOPs: 7.92 | +31: iteration 31030/ 37905 | consumed samples: 7943680 | consumed tokens: 16268656640 | elapsed time per iteration (s): 0.23 | learning rate: 3.422E-05 | global batch size: 256 | lm loss: 2.895964E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.399 | TFLOPs: 6.98 | +31: iteration 31040/ 37905 | consumed samples: 7946240 | consumed tokens: 16273899520 | elapsed time per iteration (s): 0.25 | learning rate: 3.418E-05 | global batch size: 256 | lm loss: 2.967945E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1004.585 | TFLOPs: 6.40 | +31: iteration 31050/ 37905 | consumed samples: 7948800 | consumed tokens: 16279142400 | elapsed time per iteration (s): 0.24 | learning rate: 3.414E-05 | global batch size: 256 | lm loss: 2.896289E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.652 | TFLOPs: 6.85 | +31: iteration 31060/ 37905 | consumed samples: 7951360 | consumed tokens: 16284385280 | elapsed time per iteration (s): 0.22 | learning rate: 3.410E-05 | global batch size: 256 | lm loss: 2.885232E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.455 | TFLOPs: 7.38 | +31: iteration 31070/ 37905 | consumed samples: 7953920 | consumed tokens: 16289628160 | elapsed time per iteration (s): 0.23 | learning rate: 3.406E-05 | global batch size: 256 | lm loss: 2.945087E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1106.479 | TFLOPs: 7.05 | +31: iteration 31080/ 37905 | consumed samples: 7956480 | consumed tokens: 16294871040 | elapsed time per iteration (s): 0.25 | learning rate: 3.402E-05 | global batch size: 256 | lm loss: 2.924548E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.201 | TFLOPs: 6.45 | +31: iteration 31090/ 37905 | consumed samples: 7959040 | consumed tokens: 16300113920 | elapsed time per iteration (s): 0.23 | learning rate: 3.398E-05 | global batch size: 256 | lm loss: 2.915745E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.560 | TFLOPs: 7.00 | +31: iteration 31100/ 37905 | consumed samples: 7961600 | consumed tokens: 16305356800 | elapsed time per iteration (s): 0.25 | learning rate: 3.394E-05 | global batch size: 256 | lm loss: 2.889290E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.832 | TFLOPs: 6.62 | +31: iteration 31110/ 37905 | consumed samples: 7964160 | consumed tokens: 16310599680 | elapsed time per iteration (s): 0.23 | learning rate: 3.390E-05 | global batch size: 256 | lm loss: 2.917711E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1128.634 | TFLOPs: 7.19 | +31: iteration 31120/ 37905 | consumed samples: 7966720 | consumed tokens: 16315842560 | elapsed time per iteration (s): 0.21 | learning rate: 3.386E-05 | global batch size: 256 | lm loss: 2.891516E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.612 | TFLOPs: 7.93 | +31: iteration 31130/ 37905 | consumed samples: 7969280 | consumed tokens: 16321085440 | elapsed time per iteration (s): 0.23 | learning rate: 3.382E-05 | global batch size: 256 | lm loss: 2.937826E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.194 | TFLOPs: 7.16 | +31: iteration 31140/ 37905 | consumed samples: 7971840 | consumed tokens: 16326328320 | elapsed time per iteration (s): 0.25 | learning rate: 3.378E-05 | global batch size: 256 | lm loss: 2.899946E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.313 | TFLOPs: 6.61 | +31: iteration 31150/ 37905 | consumed samples: 7974400 | consumed tokens: 16331571200 | elapsed time per iteration (s): 0.21 | learning rate: 3.374E-05 | global batch size: 256 | lm loss: 2.884999E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.024 | TFLOPs: 7.71 | +31: iteration 31160/ 37905 | consumed samples: 7976960 | consumed tokens: 16336814080 | elapsed time per iteration (s): 0.22 | learning rate: 3.370E-05 | global batch size: 256 | lm loss: 2.893472E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.924 | TFLOPs: 7.43 | +31: iteration 31170/ 37905 | consumed samples: 7979520 | consumed tokens: 16342056960 | elapsed time per iteration (s): 0.21 | learning rate: 3.366E-05 | global batch size: 256 | lm loss: 2.899594E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.025 | TFLOPs: 7.80 | +31: iteration 31180/ 37905 | consumed samples: 7982080 | consumed tokens: 16347299840 | elapsed time per iteration (s): 0.21 | learning rate: 3.362E-05 | global batch size: 256 | lm loss: 2.922565E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.621 | TFLOPs: 7.80 | +31: iteration 31190/ 37905 | consumed samples: 7984640 | consumed tokens: 16352542720 | elapsed time per iteration (s): 0.23 | learning rate: 3.358E-05 | global batch size: 256 | lm loss: 2.890310E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.904 | TFLOPs: 7.00 | +31: iteration 31200/ 37905 | consumed samples: 7987200 | consumed tokens: 16357785600 | elapsed time per iteration (s): 0.22 | learning rate: 3.354E-05 | global batch size: 256 | lm loss: 2.898575E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.888 | TFLOPs: 7.35 | +31: iteration 31210/ 37905 | consumed samples: 7989760 | consumed tokens: 16363028480 | elapsed time per iteration (s): 0.21 | learning rate: 3.350E-05 | global batch size: 256 | lm loss: 2.882575E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.311 | TFLOPs: 7.72 | +31: iteration 31220/ 37905 | consumed samples: 7992320 | consumed tokens: 16368271360 | elapsed time per iteration (s): 0.25 | learning rate: 3.346E-05 | global batch size: 256 | lm loss: 2.912546E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.587 | TFLOPs: 6.61 | +31: iteration 31230/ 37905 | consumed samples: 7994880 | consumed tokens: 16373514240 | elapsed time per iteration (s): 0.23 | learning rate: 3.343E-05 | global batch size: 256 | lm loss: 2.898969E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.792 | TFLOPs: 7.13 | +31: iteration 31240/ 37905 | consumed samples: 7997440 | consumed tokens: 16378757120 | elapsed time per iteration (s): 0.21 | learning rate: 3.339E-05 | global batch size: 256 | lm loss: 2.916994E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.908 | TFLOPs: 7.88 | +31: iteration 31250/ 37905 | consumed samples: 8000000 | consumed tokens: 16384000000 | elapsed time per iteration (s): 0.22 | learning rate: 3.335E-05 | global batch size: 256 | lm loss: 2.887360E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.449 | TFLOPs: 7.56 | +31: iteration 31260/ 37905 | consumed samples: 8002560 | consumed tokens: 16389242880 | elapsed time per iteration (s): 0.22 | learning rate: 3.331E-05 | global batch size: 256 | lm loss: 2.865984E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.816 | TFLOPs: 7.45 | +31: iteration 31270/ 37905 | consumed samples: 8005120 | consumed tokens: 16394485760 | elapsed time per iteration (s): 0.20 | learning rate: 3.327E-05 | global batch size: 256 | lm loss: 2.867770E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.807 | TFLOPs: 8.22 | +31: iteration 31280/ 37905 | consumed samples: 8007680 | consumed tokens: 16399728640 | elapsed time per iteration (s): 0.20 | learning rate: 3.323E-05 | global batch size: 256 | lm loss: 2.876937E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.759 | TFLOPs: 7.96 | +31: iteration 31290/ 37905 | consumed samples: 8010240 | consumed tokens: 16404971520 | elapsed time per iteration (s): 0.20 | learning rate: 3.319E-05 | global batch size: 256 | lm loss: 2.867226E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1250.893 | TFLOPs: 7.97 | +31: iteration 31300/ 37905 | consumed samples: 8012800 | consumed tokens: 16410214400 | elapsed time per iteration (s): 0.20 | learning rate: 3.315E-05 | global batch size: 256 | lm loss: 2.902628E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1254.150 | TFLOPs: 7.99 | +31: iteration 31310/ 37905 | consumed samples: 8015360 | consumed tokens: 16415457280 | elapsed time per iteration (s): 0.22 | learning rate: 3.311E-05 | global batch size: 256 | lm loss: 2.852709E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.936 | TFLOPs: 7.51 | +31: iteration 31320/ 37905 | consumed samples: 8017920 | consumed tokens: 16420700160 | elapsed time per iteration (s): 0.23 | learning rate: 3.307E-05 | global batch size: 256 | lm loss: 2.920903E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1137.705 | TFLOPs: 7.25 | +31: iteration 31330/ 37905 | consumed samples: 8020480 | consumed tokens: 16425943040 | elapsed time per iteration (s): 0.22 | learning rate: 3.304E-05 | global batch size: 256 | lm loss: 2.878363E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.499 | TFLOPs: 7.38 | +31: iteration 31340/ 37905 | consumed samples: 8023040 | consumed tokens: 16431185920 | elapsed time per iteration (s): 0.22 | learning rate: 3.300E-05 | global batch size: 256 | lm loss: 2.927002E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.939 | TFLOPs: 7.51 | +31: iteration 31350/ 37905 | consumed samples: 8025600 | consumed tokens: 16436428800 | elapsed time per iteration (s): 0.24 | learning rate: 3.296E-05 | global batch size: 256 | lm loss: 2.881923E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.785 | TFLOPs: 6.80 | +31: iteration 31360/ 37905 | consumed samples: 8028160 | consumed tokens: 16441671680 | elapsed time per iteration (s): 0.22 | learning rate: 3.292E-05 | global batch size: 256 | lm loss: 2.922694E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.563 | TFLOPs: 7.31 | +31: iteration 31370/ 37905 | consumed samples: 8030720 | consumed tokens: 16446914560 | elapsed time per iteration (s): 0.22 | learning rate: 3.288E-05 | global batch size: 256 | lm loss: 2.881703E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.023 | TFLOPs: 7.42 | +31: iteration 31380/ 37905 | consumed samples: 8033280 | consumed tokens: 16452157440 | elapsed time per iteration (s): 0.24 | learning rate: 3.284E-05 | global batch size: 256 | lm loss: 2.876108E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1069.319 | TFLOPs: 6.81 | +31: iteration 31390/ 37905 | consumed samples: 8035840 | consumed tokens: 16457400320 | elapsed time per iteration (s): 0.20 | learning rate: 3.280E-05 | global batch size: 256 | lm loss: 2.919652E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.902 | TFLOPs: 8.06 | +31: iteration 31400/ 37905 | consumed samples: 8038400 | consumed tokens: 16462643200 | elapsed time per iteration (s): 0.24 | learning rate: 3.277E-05 | global batch size: 256 | lm loss: 2.885539E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.045 | TFLOPs: 6.78 | +31: iteration 31410/ 37905 | consumed samples: 8040960 | consumed tokens: 16467886080 | elapsed time per iteration (s): 0.25 | learning rate: 3.273E-05 | global batch size: 256 | lm loss: 2.891969E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.250 | TFLOPs: 6.57 | +31: iteration 31420/ 37905 | consumed samples: 8043520 | consumed tokens: 16473128960 | elapsed time per iteration (s): 0.26 | learning rate: 3.269E-05 | global batch size: 256 | lm loss: 2.881293E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 997.390 | TFLOPs: 6.35 | +31: iteration 31430/ 37905 | consumed samples: 8046080 | consumed tokens: 16478371840 | elapsed time per iteration (s): 0.24 | learning rate: 3.265E-05 | global batch size: 256 | lm loss: 2.925619E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.973 | TFLOPs: 6.74 | +31: iteration 31440/ 37905 | consumed samples: 8048640 | consumed tokens: 16483614720 | elapsed time per iteration (s): 0.22 | learning rate: 3.261E-05 | global batch size: 256 | lm loss: 2.900566E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.050 | TFLOPs: 7.30 | +31: iteration 31450/ 37905 | consumed samples: 8051200 | consumed tokens: 16488857600 | elapsed time per iteration (s): 0.20 | learning rate: 3.258E-05 | global batch size: 256 | lm loss: 2.875369E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.979 | TFLOPs: 8.25 | +31: iteration 31460/ 37905 | consumed samples: 8053760 | consumed tokens: 16494100480 | elapsed time per iteration (s): 0.23 | learning rate: 3.254E-05 | global batch size: 256 | lm loss: 2.926355E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.257 | TFLOPs: 7.05 | +31: iteration 31470/ 37905 | consumed samples: 8056320 | consumed tokens: 16499343360 | elapsed time per iteration (s): 0.24 | learning rate: 3.250E-05 | global batch size: 256 | lm loss: 2.935105E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.891 | TFLOPs: 6.88 | +31: iteration 31480/ 37905 | consumed samples: 8058880 | consumed tokens: 16504586240 | elapsed time per iteration (s): 0.26 | learning rate: 3.246E-05 | global batch size: 256 | lm loss: 2.906981E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 966.887 | TFLOPs: 6.16 | +31: iteration 31490/ 37905 | consumed samples: 8061440 | consumed tokens: 16509829120 | elapsed time per iteration (s): 0.21 | learning rate: 3.242E-05 | global batch size: 256 | lm loss: 2.879137E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.118 | TFLOPs: 7.85 | +31: iteration 31500/ 37905 | consumed samples: 8064000 | consumed tokens: 16515072000 | elapsed time per iteration (s): 0.22 | learning rate: 3.239E-05 | global batch size: 256 | lm loss: 2.898677E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1189.292 | TFLOPs: 7.57 | +31: iteration 31510/ 37905 | consumed samples: 8066560 | consumed tokens: 16520314880 | elapsed time per iteration (s): 0.22 | learning rate: 3.235E-05 | global batch size: 256 | lm loss: 2.943179E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.291 | TFLOPs: 7.43 | +31: iteration 31520/ 37905 | consumed samples: 8069120 | consumed tokens: 16525557760 | elapsed time per iteration (s): 0.22 | learning rate: 3.231E-05 | global batch size: 256 | lm loss: 2.846639E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.422 | TFLOPs: 7.25 | +31: iteration 31530/ 37905 | consumed samples: 8071680 | consumed tokens: 16530800640 | elapsed time per iteration (s): 0.22 | learning rate: 3.227E-05 | global batch size: 256 | lm loss: 2.864131E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.075 | TFLOPs: 7.38 | +31: iteration 31540/ 37905 | consumed samples: 8074240 | consumed tokens: 16536043520 | elapsed time per iteration (s): 0.23 | learning rate: 3.224E-05 | global batch size: 256 | lm loss: 2.887860E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.216 | TFLOPs: 6.98 | +31: iteration 31550/ 37905 | consumed samples: 8076800 | consumed tokens: 16541286400 | elapsed time per iteration (s): 0.22 | learning rate: 3.220E-05 | global batch size: 256 | lm loss: 2.898021E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1184.615 | TFLOPs: 7.54 | +31: iteration 31560/ 37905 | consumed samples: 8079360 | consumed tokens: 16546529280 | elapsed time per iteration (s): 0.21 | learning rate: 3.216E-05 | global batch size: 256 | lm loss: 2.903541E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.197 | TFLOPs: 7.80 | +31: iteration 31570/ 37905 | consumed samples: 8081920 | consumed tokens: 16551772160 | elapsed time per iteration (s): 0.26 | learning rate: 3.212E-05 | global batch size: 256 | lm loss: 2.881714E+00 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.236 | TFLOPs: 6.31 | +31: iteration 31580/ 37905 | consumed samples: 8084480 | consumed tokens: 16557015040 | elapsed time per iteration (s): 0.25 | learning rate: 3.209E-05 | global batch size: 256 | lm loss: 2.902290E+00 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.934 | TFLOPs: 6.43 | +31: iteration 31590/ 37905 | consumed samples: 8087040 | consumed tokens: 16562257920 | elapsed time per iteration (s): 0.21 | learning rate: 3.205E-05 | global batch size: 256 | lm loss: 2.883393E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.522 | TFLOPs: 7.67 | +31: iteration 31600/ 37905 | consumed samples: 8089600 | consumed tokens: 16567500800 | elapsed time per iteration (s): 0.21 | learning rate: 3.201E-05 | global batch size: 256 | lm loss: 2.873896E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.828 | TFLOPs: 7.81 | +31: iteration 31610/ 37905 | consumed samples: 8092160 | consumed tokens: 16572743680 | elapsed time per iteration (s): 0.20 | learning rate: 3.197E-05 | global batch size: 256 | lm loss: 2.871644E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.079 | TFLOPs: 8.06 | +31: iteration 31620/ 37905 | consumed samples: 8094720 | consumed tokens: 16577986560 | elapsed time per iteration (s): 0.21 | learning rate: 3.194E-05 | global batch size: 256 | lm loss: 2.913411E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1199.506 | TFLOPs: 7.64 | +31: iteration 31630/ 37905 | consumed samples: 8097280 | consumed tokens: 16583229440 | elapsed time per iteration (s): 0.23 | learning rate: 3.190E-05 | global batch size: 256 | lm loss: 2.899177E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.188 | TFLOPs: 6.98 | +31: iteration 31640/ 37905 | consumed samples: 8099840 | consumed tokens: 16588472320 | elapsed time per iteration (s): 0.21 | learning rate: 3.186E-05 | global batch size: 256 | lm loss: 2.897166E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.493 | TFLOPs: 7.66 | +31: iteration 31650/ 37905 | consumed samples: 8102400 | consumed tokens: 16593715200 | elapsed time per iteration (s): 0.23 | learning rate: 3.183E-05 | global batch size: 256 | lm loss: 2.892032E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.544 | TFLOPs: 7.03 | +31: iteration 31660/ 37905 | consumed samples: 8104960 | consumed tokens: 16598958080 | elapsed time per iteration (s): 0.23 | learning rate: 3.179E-05 | global batch size: 256 | lm loss: 2.878676E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.780 | TFLOPs: 7.20 | +31: iteration 31670/ 37905 | consumed samples: 8107520 | consumed tokens: 16604200960 | elapsed time per iteration (s): 0.21 | learning rate: 3.175E-05 | global batch size: 256 | lm loss: 2.909344E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.209 | TFLOPs: 7.78 | +31: iteration 31680/ 37905 | consumed samples: 8110080 | consumed tokens: 16609443840 | elapsed time per iteration (s): 0.21 | learning rate: 3.172E-05 | global batch size: 256 | lm loss: 2.875249E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.425 | TFLOPs: 7.61 | +31: iteration 31690/ 37905 | consumed samples: 8112640 | consumed tokens: 16614686720 | elapsed time per iteration (s): 0.23 | learning rate: 3.168E-05 | global batch size: 256 | lm loss: 2.912441E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.227 | TFLOPs: 7.15 | +31: iteration 31700/ 37905 | consumed samples: 8115200 | consumed tokens: 16619929600 | elapsed time per iteration (s): 0.20 | learning rate: 3.164E-05 | global batch size: 256 | lm loss: 2.872593E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1296.421 | TFLOPs: 8.26 | +31: iteration 31710/ 37905 | consumed samples: 8117760 | consumed tokens: 16625172480 | elapsed time per iteration (s): 0.24 | learning rate: 3.161E-05 | global batch size: 256 | lm loss: 2.894892E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.777 | TFLOPs: 6.74 | +31: iteration 31720/ 37905 | consumed samples: 8120320 | consumed tokens: 16630415360 | elapsed time per iteration (s): 0.23 | learning rate: 3.157E-05 | global batch size: 256 | lm loss: 2.930011E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.185 | TFLOPs: 7.13 | +31: iteration 31730/ 37905 | consumed samples: 8122880 | consumed tokens: 16635658240 | elapsed time per iteration (s): 0.22 | learning rate: 3.153E-05 | global batch size: 256 | lm loss: 2.922249E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.061 | TFLOPs: 7.53 | +31: iteration 31740/ 37905 | consumed samples: 8125440 | consumed tokens: 16640901120 | elapsed time per iteration (s): 0.25 | learning rate: 3.150E-05 | global batch size: 256 | lm loss: 2.915943E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1004.754 | TFLOPs: 6.40 | +31: iteration 31750/ 37905 | consumed samples: 8128000 | consumed tokens: 16646144000 | elapsed time per iteration (s): 0.21 | learning rate: 3.146E-05 | global batch size: 256 | lm loss: 2.886273E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.900 | TFLOPs: 7.85 | +31: iteration 31760/ 37905 | consumed samples: 8130560 | consumed tokens: 16651386880 | elapsed time per iteration (s): 0.21 | learning rate: 3.142E-05 | global batch size: 256 | lm loss: 2.933551E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.694 | TFLOPs: 7.81 | +31: iteration 31770/ 37905 | consumed samples: 8133120 | consumed tokens: 16656629760 | elapsed time per iteration (s): 0.20 | learning rate: 3.139E-05 | global batch size: 256 | lm loss: 2.886176E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.137 | TFLOPs: 8.06 | +31: iteration 31780/ 37905 | consumed samples: 8135680 | consumed tokens: 16661872640 | elapsed time per iteration (s): 0.21 | learning rate: 3.135E-05 | global batch size: 256 | lm loss: 2.907578E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.695 | TFLOPs: 7.70 | +31: iteration 31790/ 37905 | consumed samples: 8138240 | consumed tokens: 16667115520 | elapsed time per iteration (s): 0.21 | learning rate: 3.131E-05 | global batch size: 256 | lm loss: 2.907431E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1192.064 | TFLOPs: 7.59 | +31: iteration 31800/ 37905 | consumed samples: 8140800 | consumed tokens: 16672358400 | elapsed time per iteration (s): 0.24 | learning rate: 3.128E-05 | global batch size: 256 | lm loss: 2.908729E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.195 | TFLOPs: 6.91 | +31: iteration 31810/ 37905 | consumed samples: 8143360 | consumed tokens: 16677601280 | elapsed time per iteration (s): 0.24 | learning rate: 3.124E-05 | global batch size: 256 | lm loss: 2.890994E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.837 | TFLOPs: 6.76 | +31: iteration 31820/ 37905 | consumed samples: 8145920 | consumed tokens: 16682844160 | elapsed time per iteration (s): 0.24 | learning rate: 3.121E-05 | global batch size: 256 | lm loss: 2.897678E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.946 | TFLOPs: 6.83 | +31: iteration 31830/ 37905 | consumed samples: 8148480 | consumed tokens: 16688087040 | elapsed time per iteration (s): 0.26 | learning rate: 3.117E-05 | global batch size: 256 | lm loss: 2.928099E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.916 | TFLOPs: 6.37 | +31: iteration 31840/ 37905 | consumed samples: 8151040 | consumed tokens: 16693329920 | elapsed time per iteration (s): 0.22 | learning rate: 3.113E-05 | global batch size: 256 | lm loss: 2.890185E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1188.647 | TFLOPs: 7.57 | +31: iteration 31850/ 37905 | consumed samples: 8153600 | consumed tokens: 16698572800 | elapsed time per iteration (s): 0.21 | learning rate: 3.110E-05 | global batch size: 256 | lm loss: 2.903137E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.689 | TFLOPs: 7.60 | +31: iteration 31860/ 37905 | consumed samples: 8156160 | consumed tokens: 16703815680 | elapsed time per iteration (s): 0.22 | learning rate: 3.106E-05 | global batch size: 256 | lm loss: 2.859762E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.976 | TFLOPs: 7.29 | +31: iteration 31870/ 37905 | consumed samples: 8158720 | consumed tokens: 16709058560 | elapsed time per iteration (s): 0.23 | learning rate: 3.103E-05 | global batch size: 256 | lm loss: 2.890896E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1137.139 | TFLOPs: 7.24 | +31: iteration 31880/ 37905 | consumed samples: 8161280 | consumed tokens: 16714301440 | elapsed time per iteration (s): 0.21 | learning rate: 3.099E-05 | global batch size: 256 | lm loss: 2.890553E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.814 | TFLOPs: 7.69 | +31: iteration 31890/ 37905 | consumed samples: 8163840 | consumed tokens: 16719544320 | elapsed time per iteration (s): 0.21 | learning rate: 3.095E-05 | global batch size: 256 | lm loss: 2.866895E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.789 | TFLOPs: 7.78 | +31: iteration 31900/ 37905 | consumed samples: 8166400 | consumed tokens: 16724787200 | elapsed time per iteration (s): 0.21 | learning rate: 3.092E-05 | global batch size: 256 | lm loss: 2.928017E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.490 | TFLOPs: 7.66 | +31: iteration 31910/ 37905 | consumed samples: 8168960 | consumed tokens: 16730030080 | elapsed time per iteration (s): 0.26 | learning rate: 3.088E-05 | global batch size: 256 | lm loss: 2.910725E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 994.266 | TFLOPs: 6.33 | +31: iteration 31920/ 37905 | consumed samples: 8171520 | consumed tokens: 16735272960 | elapsed time per iteration (s): 0.25 | learning rate: 3.085E-05 | global batch size: 256 | lm loss: 2.865508E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.480 | TFLOPs: 6.64 | +31: iteration 31930/ 37905 | consumed samples: 8174080 | consumed tokens: 16740515840 | elapsed time per iteration (s): 0.23 | learning rate: 3.081E-05 | global batch size: 256 | lm loss: 2.897776E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.728 | TFLOPs: 7.04 | +31: iteration 31940/ 37905 | consumed samples: 8176640 | consumed tokens: 16745758720 | elapsed time per iteration (s): 0.23 | learning rate: 3.078E-05 | global batch size: 256 | lm loss: 2.911761E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.537 | TFLOPs: 7.17 | +31: iteration 31950/ 37905 | consumed samples: 8179200 | consumed tokens: 16751001600 | elapsed time per iteration (s): 0.22 | learning rate: 3.074E-05 | global batch size: 256 | lm loss: 2.874423E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.756 | TFLOPs: 7.37 | +31: iteration 31960/ 37905 | consumed samples: 8181760 | consumed tokens: 16756244480 | elapsed time per iteration (s): 0.23 | learning rate: 3.071E-05 | global batch size: 256 | lm loss: 2.860785E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.321 | TFLOPs: 6.98 | +31: iteration 31970/ 37905 | consumed samples: 8184320 | consumed tokens: 16761487360 | elapsed time per iteration (s): 0.21 | learning rate: 3.067E-05 | global batch size: 256 | lm loss: 2.921423E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.042 | TFLOPs: 7.76 | +31: iteration 31980/ 37905 | consumed samples: 8186880 | consumed tokens: 16766730240 | elapsed time per iteration (s): 0.24 | learning rate: 3.064E-05 | global batch size: 256 | lm loss: 2.893129E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.734 | TFLOPs: 6.83 | +31: iteration 31990/ 37905 | consumed samples: 8189440 | consumed tokens: 16771973120 | elapsed time per iteration (s): 0.22 | learning rate: 3.060E-05 | global batch size: 256 | lm loss: 2.900434E+00 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.274 | TFLOPs: 7.55 | + 0: [2022-11-24 16:07:53,476] [INFO] [logging.py:68:log_dist] [Rank 0] step=32000, skipped=0, lr=[3.0565329883351826e-05, 3.0565329883351826e-05, 3.0565329883351826e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 32000/ 37905 | consumed samples: 8192000 | consumed tokens: 16777216000 | elapsed time per iteration (s): 0.23 | learning rate: 3.057E-05 | global batch size: 256 | lm loss: 2.869200E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.942 | TFLOPs: 7.02 | + 0: steps: 32000 loss: 2.7955 iter time (s): 0.224 samples/sec: 1145.396 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 32000 | lm loss value: 2.698611E+00 | lm loss PPL: 1.485907E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 32000 to checkpoints_83m + 0: [2022-11-24 16:07:53,581] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step32000 is begin to save! + 0: [2022-11-24 16:07:53,593] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,681] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,681] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,693] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,704] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,715] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,726] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,737] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,748] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,759] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,780] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:07:53,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:07:53,782] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step32000/mp_rank_00_model_states.pt + 0: [2022-11-24 16:07:53,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:07:53,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:07:53,850] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:07:53,849] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step32000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:07:53,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,856] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,856] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 4: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +13: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,857] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,857] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,858] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,858] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 16:07:53,858] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:07:53,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: [2022-11-24 16:07:53,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 8: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,859] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:07:53,859] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:07:53,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 3: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:07:53,860] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +29: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 9: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +20: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +20: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,861] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 16:07:53,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 4: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 7: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 7: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +17: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,862] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +31: [2022-11-24 16:07:53,862] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +14: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,863] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,863] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:07:53,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: [2022-11-24 16:07:53,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +30: [2022-11-24 16:07:53,864] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,864] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 16:07:53,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:07:53,865] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,865] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 8: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +26: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:07:53,866] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +21: [2022-11-24 16:07:53,866] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 3: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +29: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:07:53,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,867] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,867] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:07:53,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 9: [2022-11-24 16:07:53,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 4: [2022-11-24 16:07:53,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,868] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 6: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +28: [2022-11-24 16:07:53,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,869] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,869] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +14: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +31: [2022-11-24 16:07:53,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +17: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,870] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,870] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:07:53,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,871] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +30: [2022-11-24 16:07:53,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:07:53,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,872] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:07:53,872] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,872] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 8: [2022-11-24 16:07:53,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:07:53,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:07:53,873] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 16:07:53,874] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +21: [2022-11-24 16:07:53,873] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,874] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,874] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +29: [2022-11-24 16:07:53,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:07:53,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,874] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,874] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,874] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,874] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:07:53,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 3: [2022-11-24 16:07:53,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,875] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 16:07:53,875] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 9: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,876] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 7: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,876] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 4: [2022-11-24 16:07:53,876] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 6: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,876] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,876] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +28: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +14: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,877] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 16:07:53,877] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +31: [2022-11-24 16:07:53,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +17: [2022-11-24 16:07:53,878] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,878] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:07:53,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +30: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:07:53,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,879] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:07:53,880] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:07:53,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +12: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +21: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +29: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 3: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:07:53,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,881] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 16:07:53,881] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 9: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:07:53,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:07:53,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 4: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,882] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,882] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 7: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 6: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,883] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,883] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +28: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +14: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:07:53,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +17: [2022-11-24 16:07:53,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,884] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 16:07:53,884] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:07:53,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +30: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,885] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,885] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:07:53,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,886] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 8: [2022-11-24 16:07:53,886] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,887] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 3: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +20: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +29: [2022-11-24 16:07:53,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +20: [2022-11-24 16:07:53,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:07:53,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 9: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,888] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,888] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:07:53,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 7: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,889] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 6: [2022-11-24 16:07:53,889] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 4: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +28: [2022-11-24 16:07:53,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,890] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +14: [2022-11-24 16:07:53,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:07:53,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +17: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +31: [2022-11-24 16:07:53,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +31: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,891] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,891] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: [2022-11-24 16:07:53,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:07:53,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +30: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,892] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,892] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,893] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 16:07:53,893] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 8: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:07:53,893] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:07:53,894] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +29: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:07:53,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 3: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,895] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,895] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,896] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 16:07:53,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 9: [2022-11-24 16:07:53,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,896] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 7: [2022-11-24 16:07:53,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,896] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,896] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 4: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,897] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +23: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,897] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +28: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,897] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:07:53,898] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 6: [2022-11-24 16:07:53,897] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,898] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,898] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:07:53,898] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 16:07:53,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +17: [2022-11-24 16:07:53,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: [2022-11-24 16:07:53,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,899] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:07:53,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,899] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:07:53,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:07:53,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +30: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,900] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,900] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:07:53,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 8: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,901] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +21: [2022-11-24 16:07:53,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:07:53,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +29: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:07:53,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:07:53,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 2: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 9: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:07:53,902] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,902] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +20: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +14: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +19: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +14: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +23: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +12: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +29: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +14: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 3: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 6: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +20: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +12: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 5: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +13: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +18: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 6: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +13: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +21: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +21: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +18: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +10: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +30: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +16: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +26: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +24: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +17: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +28: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +27: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +10: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +30: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +16: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +24: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +21: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +11: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +22: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +15: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +21: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 7: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +17: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +11: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +22: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 1: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +31: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +15: [2022-11-24 16:07:53,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +31: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,903] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +31: [2022-11-24 16:07:53,903] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! +25: [2022-11-24 16:07:53,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:07:53,904] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step32000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 16:07:53,904] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step32000 is ready now! + 0: successfully saved checkpoint at iteration 32000 to checkpoints_83m +31: time (ms) | save-checkpoint: 342.75 +31: iteration 32010/ 37905 | consumed samples: 8194560 | consumed tokens: 16782458880 | elapsed time per iteration (s): 0.25 | learning rate: 3.053E-05 | global batch size: 256 | lm loss: 2.893248E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.476 | TFLOPs: 6.65 | +31: iteration 32020/ 37905 | consumed samples: 8197120 | consumed tokens: 16787701760 | elapsed time per iteration (s): 0.25 | learning rate: 3.050E-05 | global batch size: 256 | lm loss: 2.868548E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.708 | TFLOPs: 6.58 | +31: iteration 32030/ 37905 | consumed samples: 8199680 | consumed tokens: 16792944640 | elapsed time per iteration (s): 0.24 | learning rate: 3.046E-05 | global batch size: 256 | lm loss: 2.897379E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.564 | TFLOPs: 6.92 | +31: iteration 32040/ 37905 | consumed samples: 8202240 | consumed tokens: 16798187520 | elapsed time per iteration (s): 0.23 | learning rate: 3.043E-05 | global batch size: 256 | lm loss: 2.927007E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.460 | TFLOPs: 7.03 | +31: iteration 32050/ 37905 | consumed samples: 8204800 | consumed tokens: 16803430400 | elapsed time per iteration (s): 0.21 | learning rate: 3.039E-05 | global batch size: 256 | lm loss: 2.929189E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.607 | TFLOPs: 7.76 | +31: iteration 32060/ 37905 | consumed samples: 8207360 | consumed tokens: 16808673280 | elapsed time per iteration (s): 0.21 | learning rate: 3.036E-05 | global batch size: 256 | lm loss: 2.884214E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.610 | TFLOPs: 7.88 | +31: iteration 32070/ 37905 | consumed samples: 8209920 | consumed tokens: 16813916160 | elapsed time per iteration (s): 0.19 | learning rate: 3.032E-05 | global batch size: 256 | lm loss: 2.895218E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.669 | TFLOPs: 8.39 | +31: iteration 32080/ 37905 | consumed samples: 8212480 | consumed tokens: 16819159040 | elapsed time per iteration (s): 0.24 | learning rate: 3.029E-05 | global batch size: 256 | lm loss: 2.920776E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.059 | TFLOPs: 6.86 | +31: iteration 32090/ 37905 | consumed samples: 8215040 | consumed tokens: 16824401920 | elapsed time per iteration (s): 0.19 | learning rate: 3.025E-05 | global batch size: 256 | lm loss: 2.922249E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1377.559 | TFLOPs: 8.77 | +31: iteration 32100/ 37905 | consumed samples: 8217600 | consumed tokens: 16829644800 | elapsed time per iteration (s): 0.23 | learning rate: 3.022E-05 | global batch size: 256 | lm loss: 2.906946E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.701 | TFLOPs: 7.04 | +31: iteration 32110/ 37905 | consumed samples: 8220160 | consumed tokens: 16834887680 | elapsed time per iteration (s): 0.20 | learning rate: 3.018E-05 | global batch size: 256 | lm loss: 2.898132E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.070 | TFLOPs: 7.97 | +31: iteration 32120/ 37905 | consumed samples: 8222720 | consumed tokens: 16840130560 | elapsed time per iteration (s): 0.24 | learning rate: 3.015E-05 | global batch size: 256 | lm loss: 2.891929E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.441 | TFLOPs: 6.85 | +31: iteration 32130/ 37905 | consumed samples: 8225280 | consumed tokens: 16845373440 | elapsed time per iteration (s): 0.23 | learning rate: 3.011E-05 | global batch size: 256 | lm loss: 2.940671E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.054 | TFLOPs: 6.96 | +31: iteration 32140/ 37905 | consumed samples: 8227840 | consumed tokens: 16850616320 | elapsed time per iteration (s): 0.21 | learning rate: 3.008E-05 | global batch size: 256 | lm loss: 2.847552E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.405 | TFLOPs: 7.70 | +31: iteration 32150/ 37905 | consumed samples: 8230400 | consumed tokens: 16855859200 | elapsed time per iteration (s): 0.20 | learning rate: 3.005E-05 | global batch size: 256 | lm loss: 2.880252E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1258.223 | TFLOPs: 8.01 | +31: iteration 32160/ 37905 | consumed samples: 8232960 | consumed tokens: 16861102080 | elapsed time per iteration (s): 0.23 | learning rate: 3.001E-05 | global batch size: 256 | lm loss: 2.920028E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.074 | TFLOPs: 7.15 | +31: iteration 32170/ 37905 | consumed samples: 8235520 | consumed tokens: 16866344960 | elapsed time per iteration (s): 0.22 | learning rate: 2.998E-05 | global batch size: 256 | lm loss: 2.882434E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.502 | TFLOPs: 7.56 | +31: iteration 32180/ 37905 | consumed samples: 8238080 | consumed tokens: 16871587840 | elapsed time per iteration (s): 0.21 | learning rate: 2.994E-05 | global batch size: 256 | lm loss: 2.894080E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.587 | TFLOPs: 7.79 | +31: iteration 32190/ 37905 | consumed samples: 8240640 | consumed tokens: 16876830720 | elapsed time per iteration (s): 0.22 | learning rate: 2.991E-05 | global batch size: 256 | lm loss: 2.888771E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.781 | TFLOPs: 7.56 | +31: iteration 32200/ 37905 | consumed samples: 8243200 | consumed tokens: 16882073600 | elapsed time per iteration (s): 0.23 | learning rate: 2.987E-05 | global batch size: 256 | lm loss: 2.918851E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.975 | TFLOPs: 6.98 | +31: iteration 32210/ 37905 | consumed samples: 8245760 | consumed tokens: 16887316480 | elapsed time per iteration (s): 0.23 | learning rate: 2.984E-05 | global batch size: 256 | lm loss: 2.901331E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1111.002 | TFLOPs: 7.08 | +31: iteration 32220/ 37905 | consumed samples: 8248320 | consumed tokens: 16892559360 | elapsed time per iteration (s): 0.21 | learning rate: 2.981E-05 | global batch size: 256 | lm loss: 2.886977E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.590 | TFLOPs: 7.66 | +31: iteration 32230/ 37905 | consumed samples: 8250880 | consumed tokens: 16897802240 | elapsed time per iteration (s): 0.20 | learning rate: 2.977E-05 | global batch size: 256 | lm loss: 2.874850E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.331 | TFLOPs: 8.15 | +31: iteration 32240/ 37905 | consumed samples: 8253440 | consumed tokens: 16903045120 | elapsed time per iteration (s): 0.21 | learning rate: 2.974E-05 | global batch size: 256 | lm loss: 2.910786E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1216.041 | TFLOPs: 7.74 | +31: iteration 32250/ 37905 | consumed samples: 8256000 | consumed tokens: 16908288000 | elapsed time per iteration (s): 0.24 | learning rate: 2.971E-05 | global batch size: 256 | lm loss: 2.901435E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.534 | TFLOPs: 6.83 | +31: iteration 32260/ 37905 | consumed samples: 8258560 | consumed tokens: 16913530880 | elapsed time per iteration (s): 0.23 | learning rate: 2.967E-05 | global batch size: 256 | lm loss: 2.985669E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.873 | TFLOPs: 7.16 | +31: iteration 32270/ 37905 | consumed samples: 8261120 | consumed tokens: 16918773760 | elapsed time per iteration (s): 0.19 | learning rate: 2.964E-05 | global batch size: 256 | lm loss: 2.903354E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1324.597 | TFLOPs: 8.44 | +31: iteration 32280/ 37905 | consumed samples: 8263680 | consumed tokens: 16924016640 | elapsed time per iteration (s): 0.22 | learning rate: 2.960E-05 | global batch size: 256 | lm loss: 2.879097E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.173 | TFLOPs: 7.53 | +31: iteration 32290/ 37905 | consumed samples: 8266240 | consumed tokens: 16929259520 | elapsed time per iteration (s): 0.19 | learning rate: 2.957E-05 | global batch size: 256 | lm loss: 2.912972E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1328.800 | TFLOPs: 8.46 | +31: iteration 32300/ 37905 | consumed samples: 8268800 | consumed tokens: 16934502400 | elapsed time per iteration (s): 0.23 | learning rate: 2.954E-05 | global batch size: 256 | lm loss: 2.897329E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.374 | TFLOPs: 7.21 | +31: iteration 32310/ 37905 | consumed samples: 8271360 | consumed tokens: 16939745280 | elapsed time per iteration (s): 0.21 | learning rate: 2.950E-05 | global batch size: 256 | lm loss: 2.903171E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.713 | TFLOPs: 7.58 | +31: iteration 32320/ 37905 | consumed samples: 8273920 | consumed tokens: 16944988160 | elapsed time per iteration (s): 0.20 | learning rate: 2.947E-05 | global batch size: 256 | lm loss: 2.926372E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.522 | TFLOPs: 8.24 | +31: iteration 32330/ 37905 | consumed samples: 8276480 | consumed tokens: 16950231040 | elapsed time per iteration (s): 0.24 | learning rate: 2.944E-05 | global batch size: 256 | lm loss: 2.914561E+00 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.568 | TFLOPs: 6.90 | +31: iteration 32340/ 37905 | consumed samples: 8279040 | consumed tokens: 16955473920 | elapsed time per iteration (s): 0.22 | learning rate: 2.940E-05 | global batch size: 256 | lm loss: 2.918672E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.346 | TFLOPs: 7.46 | +31: iteration 32350/ 37905 | consumed samples: 8281600 | consumed tokens: 16960716800 | elapsed time per iteration (s): 0.22 | learning rate: 2.937E-05 | global batch size: 256 | lm loss: 2.928033E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1177.667 | TFLOPs: 7.50 | +31: iteration 32360/ 37905 | consumed samples: 8284160 | consumed tokens: 16965959680 | elapsed time per iteration (s): 0.22 | learning rate: 2.934E-05 | global batch size: 256 | lm loss: 2.889442E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.195 | TFLOPs: 7.27 | +31: iteration 32370/ 37905 | consumed samples: 8286720 | consumed tokens: 16971202560 | elapsed time per iteration (s): 0.20 | learning rate: 2.931E-05 | global batch size: 256 | lm loss: 2.893496E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1285.087 | TFLOPs: 8.18 | +31: iteration 32380/ 37905 | consumed samples: 8289280 | consumed tokens: 16976445440 | elapsed time per iteration (s): 0.25 | learning rate: 2.927E-05 | global batch size: 256 | lm loss: 2.886889E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.002 | TFLOPs: 6.59 | +31: iteration 32390/ 37905 | consumed samples: 8291840 | consumed tokens: 16981688320 | elapsed time per iteration (s): 0.22 | learning rate: 2.924E-05 | global batch size: 256 | lm loss: 2.894597E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.372 | TFLOPs: 7.26 | +31: iteration 32400/ 37905 | consumed samples: 8294400 | consumed tokens: 16986931200 | elapsed time per iteration (s): 0.21 | learning rate: 2.921E-05 | global batch size: 256 | lm loss: 2.871968E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.234 | TFLOPs: 7.92 | +31: iteration 32410/ 37905 | consumed samples: 8296960 | consumed tokens: 16992174080 | elapsed time per iteration (s): 0.21 | learning rate: 2.917E-05 | global batch size: 256 | lm loss: 2.881145E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1226.177 | TFLOPs: 7.81 | +31: iteration 32420/ 37905 | consumed samples: 8299520 | consumed tokens: 16997416960 | elapsed time per iteration (s): 0.21 | learning rate: 2.914E-05 | global batch size: 256 | lm loss: 2.902729E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.065 | TFLOPs: 7.72 | +31: iteration 32430/ 37905 | consumed samples: 8302080 | consumed tokens: 17002659840 | elapsed time per iteration (s): 0.22 | learning rate: 2.911E-05 | global batch size: 256 | lm loss: 2.885486E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.390 | TFLOPs: 7.38 | +31: iteration 32440/ 37905 | consumed samples: 8304640 | consumed tokens: 17007902720 | elapsed time per iteration (s): 0.20 | learning rate: 2.908E-05 | global batch size: 256 | lm loss: 2.921100E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.564 | TFLOPs: 8.15 | +31: iteration 32450/ 37905 | consumed samples: 8307200 | consumed tokens: 17013145600 | elapsed time per iteration (s): 0.22 | learning rate: 2.904E-05 | global batch size: 256 | lm loss: 2.877965E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.366 | TFLOPs: 7.28 | +31: iteration 32460/ 37905 | consumed samples: 8309760 | consumed tokens: 17018388480 | elapsed time per iteration (s): 0.19 | learning rate: 2.901E-05 | global batch size: 256 | lm loss: 2.893481E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.678 | TFLOPs: 8.38 | +31: iteration 32470/ 37905 | consumed samples: 8312320 | consumed tokens: 17023631360 | elapsed time per iteration (s): 0.23 | learning rate: 2.898E-05 | global batch size: 256 | lm loss: 2.915620E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1090.915 | TFLOPs: 6.95 | +31: iteration 32480/ 37905 | consumed samples: 8314880 | consumed tokens: 17028874240 | elapsed time per iteration (s): 0.24 | learning rate: 2.895E-05 | global batch size: 256 | lm loss: 2.898486E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.961 | TFLOPs: 6.90 | +31: iteration 32490/ 37905 | consumed samples: 8317440 | consumed tokens: 17034117120 | elapsed time per iteration (s): 0.20 | learning rate: 2.891E-05 | global batch size: 256 | lm loss: 2.842133E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.938 | TFLOPs: 8.11 | +31: iteration 32500/ 37905 | consumed samples: 8320000 | consumed tokens: 17039360000 | elapsed time per iteration (s): 0.23 | learning rate: 2.888E-05 | global batch size: 256 | lm loss: 2.871114E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.451 | TFLOPs: 7.02 | +31: iteration 32510/ 37905 | consumed samples: 8322560 | consumed tokens: 17044602880 | elapsed time per iteration (s): 0.31 | learning rate: 2.885E-05 | global batch size: 256 | lm loss: 2.871109E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.750 | TFLOPs: 5.18 | +31: iteration 32520/ 37905 | consumed samples: 8325120 | consumed tokens: 17049845760 | elapsed time per iteration (s): 0.21 | learning rate: 2.882E-05 | global batch size: 256 | lm loss: 2.892223E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.570 | TFLOPs: 7.87 | +31: iteration 32530/ 37905 | consumed samples: 8327680 | consumed tokens: 17055088640 | elapsed time per iteration (s): 0.24 | learning rate: 2.878E-05 | global batch size: 256 | lm loss: 2.877814E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.440 | TFLOPs: 6.84 | +31: iteration 32540/ 37905 | consumed samples: 8330240 | consumed tokens: 17060331520 | elapsed time per iteration (s): 0.23 | learning rate: 2.875E-05 | global batch size: 256 | lm loss: 2.883225E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.002 | TFLOPs: 7.15 | +31: iteration 32550/ 37905 | consumed samples: 8332800 | consumed tokens: 17065574400 | elapsed time per iteration (s): 0.23 | learning rate: 2.872E-05 | global batch size: 256 | lm loss: 2.921638E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.316 | TFLOPs: 7.17 | +31: iteration 32560/ 37905 | consumed samples: 8335360 | consumed tokens: 17070817280 | elapsed time per iteration (s): 0.25 | learning rate: 2.869E-05 | global batch size: 256 | lm loss: 2.901368E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1016.843 | TFLOPs: 6.48 | +31: iteration 32570/ 37905 | consumed samples: 8337920 | consumed tokens: 17076060160 | elapsed time per iteration (s): 0.22 | learning rate: 2.866E-05 | global batch size: 256 | lm loss: 2.880804E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.953 | TFLOPs: 7.29 | +31: iteration 32580/ 37905 | consumed samples: 8340480 | consumed tokens: 17081303040 | elapsed time per iteration (s): 0.20 | learning rate: 2.862E-05 | global batch size: 256 | lm loss: 2.871731E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1291.395 | TFLOPs: 8.22 | +31: iteration 32590/ 37905 | consumed samples: 8343040 | consumed tokens: 17086545920 | elapsed time per iteration (s): 0.19 | learning rate: 2.859E-05 | global batch size: 256 | lm loss: 2.901748E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1320.709 | TFLOPs: 8.41 | +31: iteration 32600/ 37905 | consumed samples: 8345600 | consumed tokens: 17091788800 | elapsed time per iteration (s): 0.21 | learning rate: 2.856E-05 | global batch size: 256 | lm loss: 2.888920E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1203.667 | TFLOPs: 7.67 | +31: iteration 32610/ 37905 | consumed samples: 8348160 | consumed tokens: 17097031680 | elapsed time per iteration (s): 0.22 | learning rate: 2.853E-05 | global batch size: 256 | lm loss: 2.855133E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.916 | TFLOPs: 7.53 | +31: iteration 32620/ 37905 | consumed samples: 8350720 | consumed tokens: 17102274560 | elapsed time per iteration (s): 0.21 | learning rate: 2.850E-05 | global batch size: 256 | lm loss: 2.898446E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1232.637 | TFLOPs: 7.85 | +31: iteration 32630/ 37905 | consumed samples: 8353280 | consumed tokens: 17107517440 | elapsed time per iteration (s): 0.21 | learning rate: 2.847E-05 | global batch size: 256 | lm loss: 2.878386E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1240.123 | TFLOPs: 7.90 | +31: iteration 32640/ 37905 | consumed samples: 8355840 | consumed tokens: 17112760320 | elapsed time per iteration (s): 0.20 | learning rate: 2.843E-05 | global batch size: 256 | lm loss: 2.875337E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1253.228 | TFLOPs: 7.98 | +31: iteration 32650/ 37905 | consumed samples: 8358400 | consumed tokens: 17118003200 | elapsed time per iteration (s): 0.22 | learning rate: 2.840E-05 | global batch size: 256 | lm loss: 2.849918E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.801 | TFLOPs: 7.31 | +31: iteration 32660/ 37905 | consumed samples: 8360960 | consumed tokens: 17123246080 | elapsed time per iteration (s): 0.24 | learning rate: 2.837E-05 | global batch size: 256 | lm loss: 2.856539E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1054.423 | TFLOPs: 6.72 | +31: iteration 32670/ 37905 | consumed samples: 8363520 | consumed tokens: 17128488960 | elapsed time per iteration (s): 0.22 | learning rate: 2.834E-05 | global batch size: 256 | lm loss: 2.908398E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.842 | TFLOPs: 7.49 | +31: iteration 32680/ 37905 | consumed samples: 8366080 | consumed tokens: 17133731840 | elapsed time per iteration (s): 0.21 | learning rate: 2.831E-05 | global batch size: 256 | lm loss: 2.894121E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.467 | TFLOPs: 7.93 | +31: iteration 32690/ 37905 | consumed samples: 8368640 | consumed tokens: 17138974720 | elapsed time per iteration (s): 0.23 | learning rate: 2.828E-05 | global batch size: 256 | lm loss: 2.884422E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1137.720 | TFLOPs: 7.25 | +31: iteration 32700/ 37905 | consumed samples: 8371200 | consumed tokens: 17144217600 | elapsed time per iteration (s): 0.24 | learning rate: 2.825E-05 | global batch size: 256 | lm loss: 2.884761E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.321 | TFLOPs: 6.73 | +31: iteration 32710/ 37905 | consumed samples: 8373760 | consumed tokens: 17149460480 | elapsed time per iteration (s): 0.22 | learning rate: 2.821E-05 | global batch size: 256 | lm loss: 2.898284E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.443 | TFLOPs: 7.31 | +31: iteration 32720/ 37905 | consumed samples: 8376320 | consumed tokens: 17154703360 | elapsed time per iteration (s): 0.22 | learning rate: 2.818E-05 | global batch size: 256 | lm loss: 2.871688E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.143 | TFLOPs: 7.34 | +31: iteration 32730/ 37905 | consumed samples: 8378880 | consumed tokens: 17159946240 | elapsed time per iteration (s): 0.23 | learning rate: 2.815E-05 | global batch size: 256 | lm loss: 2.907176E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.227 | TFLOPs: 6.98 | +31: iteration 32740/ 37905 | consumed samples: 8381440 | consumed tokens: 17165189120 | elapsed time per iteration (s): 0.19 | learning rate: 2.812E-05 | global batch size: 256 | lm loss: 2.880353E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.584 | TFLOPs: 8.39 | +31: iteration 32750/ 37905 | consumed samples: 8384000 | consumed tokens: 17170432000 | elapsed time per iteration (s): 0.21 | learning rate: 2.809E-05 | global batch size: 256 | lm loss: 2.908449E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.926 | TFLOPs: 7.93 | +31: iteration 32760/ 37905 | consumed samples: 8386560 | consumed tokens: 17175674880 | elapsed time per iteration (s): 0.19 | learning rate: 2.806E-05 | global batch size: 256 | lm loss: 2.893411E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1314.548 | TFLOPs: 8.37 | +31: iteration 32770/ 37905 | consumed samples: 8389120 | consumed tokens: 17180917760 | elapsed time per iteration (s): 0.24 | learning rate: 2.803E-05 | global batch size: 256 | lm loss: 2.909015E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.984 | TFLOPs: 6.82 | +31: iteration 32780/ 37905 | consumed samples: 8391680 | consumed tokens: 17186160640 | elapsed time per iteration (s): 0.20 | learning rate: 2.800E-05 | global batch size: 256 | lm loss: 2.878169E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.983 | TFLOPs: 8.13 | +31: iteration 32790/ 37905 | consumed samples: 8394240 | consumed tokens: 17191403520 | elapsed time per iteration (s): 0.21 | learning rate: 2.797E-05 | global batch size: 256 | lm loss: 2.899363E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.465 | TFLOPs: 7.59 | +31: iteration 32800/ 37905 | consumed samples: 8396800 | consumed tokens: 17196646400 | elapsed time per iteration (s): 0.20 | learning rate: 2.794E-05 | global batch size: 256 | lm loss: 2.886834E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1297.309 | TFLOPs: 8.26 | +31: iteration 32810/ 37905 | consumed samples: 8399360 | consumed tokens: 17201889280 | elapsed time per iteration (s): 0.24 | learning rate: 2.791E-05 | global batch size: 256 | lm loss: 2.911230E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.105 | TFLOPs: 6.87 | +31: iteration 32820/ 37905 | consumed samples: 8401920 | consumed tokens: 17207132160 | elapsed time per iteration (s): 0.25 | learning rate: 2.788E-05 | global batch size: 256 | lm loss: 2.913069E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.968 | TFLOPs: 6.58 | +31: iteration 32830/ 37905 | consumed samples: 8404480 | consumed tokens: 17212375040 | elapsed time per iteration (s): 0.21 | learning rate: 2.784E-05 | global batch size: 256 | lm loss: 2.939316E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.257 | TFLOPs: 7.78 | +31: iteration 32840/ 37905 | consumed samples: 8407040 | consumed tokens: 17217617920 | elapsed time per iteration (s): 0.25 | learning rate: 2.781E-05 | global batch size: 256 | lm loss: 2.911461E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1042.113 | TFLOPs: 6.64 | +31: iteration 32850/ 37905 | consumed samples: 8409600 | consumed tokens: 17222860800 | elapsed time per iteration (s): 0.22 | learning rate: 2.778E-05 | global batch size: 256 | lm loss: 2.875608E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.161 | TFLOPs: 7.47 | +31: iteration 32860/ 37905 | consumed samples: 8412160 | consumed tokens: 17228103680 | elapsed time per iteration (s): 0.21 | learning rate: 2.775E-05 | global batch size: 256 | lm loss: 2.909879E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.341 | TFLOPs: 7.66 | +31: iteration 32870/ 37905 | consumed samples: 8414720 | consumed tokens: 17233346560 | elapsed time per iteration (s): 0.20 | learning rate: 2.772E-05 | global batch size: 256 | lm loss: 2.884886E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1294.950 | TFLOPs: 8.25 | +31: iteration 32880/ 37905 | consumed samples: 8417280 | consumed tokens: 17238589440 | elapsed time per iteration (s): 0.22 | learning rate: 2.769E-05 | global batch size: 256 | lm loss: 2.892169E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1176.165 | TFLOPs: 7.49 | +31: iteration 32890/ 37905 | consumed samples: 8419840 | consumed tokens: 17243832320 | elapsed time per iteration (s): 0.21 | learning rate: 2.766E-05 | global batch size: 256 | lm loss: 2.876338E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.475 | TFLOPs: 7.88 | +31: iteration 32900/ 37905 | consumed samples: 8422400 | consumed tokens: 17249075200 | elapsed time per iteration (s): 0.21 | learning rate: 2.763E-05 | global batch size: 256 | lm loss: 2.883865E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.037 | TFLOPs: 7.69 | +31: iteration 32910/ 37905 | consumed samples: 8424960 | consumed tokens: 17254318080 | elapsed time per iteration (s): 0.26 | learning rate: 2.760E-05 | global batch size: 256 | lm loss: 2.885491E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.301 | TFLOPs: 6.33 | +31: iteration 32920/ 37905 | consumed samples: 8427520 | consumed tokens: 17259560960 | elapsed time per iteration (s): 0.24 | learning rate: 2.757E-05 | global batch size: 256 | lm loss: 2.873204E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.209 | TFLOPs: 6.89 | +31: iteration 32930/ 37905 | consumed samples: 8430080 | consumed tokens: 17264803840 | elapsed time per iteration (s): 0.21 | learning rate: 2.754E-05 | global batch size: 256 | lm loss: 2.932844E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.704 | TFLOPs: 7.84 | +31: iteration 32940/ 37905 | consumed samples: 8432640 | consumed tokens: 17270046720 | elapsed time per iteration (s): 0.22 | learning rate: 2.751E-05 | global batch size: 256 | lm loss: 2.928065E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.958 | TFLOPs: 7.29 | +31: iteration 32950/ 37905 | consumed samples: 8435200 | consumed tokens: 17275289600 | elapsed time per iteration (s): 0.22 | learning rate: 2.748E-05 | global batch size: 256 | lm loss: 2.923400E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.621 | TFLOPs: 7.46 | +31: iteration 32960/ 37905 | consumed samples: 8437760 | consumed tokens: 17280532480 | elapsed time per iteration (s): 0.23 | learning rate: 2.745E-05 | global batch size: 256 | lm loss: 2.897006E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.042 | TFLOPs: 7.05 | +31: iteration 32970/ 37905 | consumed samples: 8440320 | consumed tokens: 17285775360 | elapsed time per iteration (s): 0.21 | learning rate: 2.742E-05 | global batch size: 256 | lm loss: 2.906508E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.108 | TFLOPs: 7.71 | +31: iteration 32980/ 37905 | consumed samples: 8442880 | consumed tokens: 17291018240 | elapsed time per iteration (s): 0.23 | learning rate: 2.739E-05 | global batch size: 256 | lm loss: 2.930107E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.886 | TFLOPs: 6.94 | +31: iteration 32990/ 37905 | consumed samples: 8445440 | consumed tokens: 17296261120 | elapsed time per iteration (s): 0.22 | learning rate: 2.736E-05 | global batch size: 256 | lm loss: 2.866133E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.163 | TFLOPs: 7.39 | +31: iteration 33000/ 37905 | consumed samples: 8448000 | consumed tokens: 17301504000 | elapsed time per iteration (s): 0.20 | learning rate: 2.734E-05 | global batch size: 256 | lm loss: 2.929781E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.607 | TFLOPs: 7.96 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 33000 | lm loss value: 2.799244E+00 | lm loss PPL: 1.643221E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 33000 to checkpoints_83m + 0: [2022-11-24 16:11:33,437] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step33000 is begin to save! + 0: [2022-11-24 16:11:33,448] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,532] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,543] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,554] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,565] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,576] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,576] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,587] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,598] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,609] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:11:33,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:11:33,632] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step33000/mp_rank_00_model_states.pt + 0: [2022-11-24 16:11:33,632] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:11:33,634] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:11:33,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step33000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:11:33,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:11:33,705] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:11:33,705] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,705] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:11:33,707] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,707] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +22: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:11:33,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 8: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +15: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 1: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,708] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,708] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +28: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,709] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 3: [2022-11-24 16:11:33,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +16: [2022-11-24 16:11:33,710] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,710] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +11: [2022-11-24 16:11:33,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:11:33,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,711] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,711] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +21: [2022-11-24 16:11:33,712] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,713] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,713] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +22: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:11:33,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +19: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 8: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +15: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,714] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:11:33,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:11:33,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,715] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +28: [2022-11-24 16:11:33,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +25: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 1: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:11:33,716] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,716] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +10: [2022-11-24 16:11:33,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +11: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,717] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 16:11:33,717] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 3: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +16: [2022-11-24 16:11:33,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:11:33,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +18: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:11:33,718] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 16:11:33,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +21: [2022-11-24 16:11:33,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:11:33,719] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +22: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,720] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +17: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:11:33,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +19: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:11:33,721] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +15: [2022-11-24 16:11:33,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 8: [2022-11-24 16:11:33,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,722] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:11:33,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 1: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:11:33,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +25: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,723] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +10: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +16: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,724] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 16:11:33,724] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 3: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +18: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +11: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,725] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:11:33,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +21: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,726] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:11:33,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +17: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,727] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 16:11:33,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:11:33,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +22: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:11:33,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +19: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,728] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,728] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +15: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:11:33,729] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +25: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +28: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 1: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +10: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,730] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,731] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,731] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,731] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +16: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +11: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +18: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +18: [2022-11-24 16:11:33,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:11:33,732] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,733] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,733] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:11:33,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,734] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,734] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,734] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:11:33,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +17: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +22: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +15: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,735] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 8: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:11:33,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,736] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,736] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +25: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 1: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +28: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,737] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:11:33,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,738] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:11:33,738] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +10: [2022-11-24 16:11:33,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:11:33,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +16: [2022-11-24 16:11:33,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,739] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +16: [2022-11-24 16:11:33,739] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +11: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 3: [2022-11-24 16:11:33,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:11:33,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +18: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +12: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,740] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +18: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +21: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:11:33,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:11:33,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +17: [2022-11-24 16:11:33,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +22: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:11:33,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:11:33,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +15: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 8: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:11:33,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:11:33,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +28: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +25: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:11:33,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +10: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +11: [2022-11-24 16:11:33,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 3: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:11:33,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +18: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:11:33,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:11:33,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +21: [2022-11-24 16:11:33,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 16:11:33,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:11:33,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:11:33,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:11:33,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +22: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +17: [2022-11-24 16:11:33,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +15: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:11:33,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +19: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 8: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +28: [2022-11-24 16:11:33,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 1: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +23: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:11:33,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +25: [2022-11-24 16:11:33,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +10: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +16: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 3: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:11:33,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:11:33,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +14: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +12: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +30: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +23: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +18: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +10: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +14: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +17: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +30: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +17: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +14: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 8: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +30: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +20: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +18: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +11: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +12: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +22: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 6: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 4: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +11: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +10: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +30: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +19: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +26: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +15: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +21: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 9: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +31: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +19: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +26: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +24: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +21: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +31: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 2: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 7: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +27: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +19: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +13: [2022-11-24 16:11:33,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +24: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 5: [2022-11-24 16:11:33,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +27: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +25: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +19: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:11:33,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:11:33,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +20: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +13: [2022-11-24 16:11:33,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +13: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +29: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:11:33,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 16:11:33,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! +28: [2022-11-24 16:11:33,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:11:33,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step33000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 16:11:33,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step33000 is ready now! + 0: successfully saved checkpoint at iteration 33000 to checkpoints_83m +31: time (ms) | save-checkpoint: 333.32 +31: iteration 33010/ 37905 | consumed samples: 8450560 | consumed tokens: 17306746880 | elapsed time per iteration (s): 0.23 | learning rate: 2.731E-05 | global batch size: 256 | lm loss: 2.919646E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.254 | TFLOPs: 7.17 | +31: iteration 33020/ 37905 | consumed samples: 8453120 | consumed tokens: 17311989760 | elapsed time per iteration (s): 0.21 | learning rate: 2.728E-05 | global batch size: 256 | lm loss: 2.918966E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.391 | TFLOPs: 7.65 | +31: iteration 33030/ 37905 | consumed samples: 8455680 | consumed tokens: 17317232640 | elapsed time per iteration (s): 0.21 | learning rate: 2.725E-05 | global batch size: 256 | lm loss: 2.909912E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.661 | TFLOPs: 7.74 | +31: iteration 33040/ 37905 | consumed samples: 8458240 | consumed tokens: 17322475520 | elapsed time per iteration (s): 0.22 | learning rate: 2.722E-05 | global batch size: 256 | lm loss: 2.869808E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.736 | TFLOPs: 7.30 | +31: iteration 33050/ 37905 | consumed samples: 8460800 | consumed tokens: 17327718400 | elapsed time per iteration (s): 0.24 | learning rate: 2.719E-05 | global batch size: 256 | lm loss: 2.858209E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.675 | TFLOPs: 6.88 | +31: iteration 33060/ 37905 | consumed samples: 8463360 | consumed tokens: 17332961280 | elapsed time per iteration (s): 0.21 | learning rate: 2.716E-05 | global batch size: 256 | lm loss: 2.879974E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.070 | TFLOPs: 7.92 | +31: iteration 33070/ 37905 | consumed samples: 8465920 | consumed tokens: 17338204160 | elapsed time per iteration (s): 0.22 | learning rate: 2.713E-05 | global batch size: 256 | lm loss: 2.898798E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.508 | TFLOPs: 7.47 | +31: iteration 33080/ 37905 | consumed samples: 8468480 | consumed tokens: 17343447040 | elapsed time per iteration (s): 0.25 | learning rate: 2.710E-05 | global batch size: 256 | lm loss: 2.850879E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1043.111 | TFLOPs: 6.64 | +31: iteration 33090/ 37905 | consumed samples: 8471040 | consumed tokens: 17348689920 | elapsed time per iteration (s): 0.22 | learning rate: 2.707E-05 | global batch size: 256 | lm loss: 2.906181E+00 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1142.538 | TFLOPs: 7.28 | +31: iteration 33100/ 37905 | consumed samples: 8473600 | consumed tokens: 17353932800 | elapsed time per iteration (s): 0.24 | learning rate: 2.704E-05 | global batch size: 256 | lm loss: 2.892702E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.901 | TFLOPs: 6.67 | +31: iteration 33110/ 37905 | consumed samples: 8476160 | consumed tokens: 17359175680 | elapsed time per iteration (s): 0.23 | learning rate: 2.701E-05 | global batch size: 256 | lm loss: 2.895300E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.792 | TFLOPs: 6.97 | +31: iteration 33120/ 37905 | consumed samples: 8478720 | consumed tokens: 17364418560 | elapsed time per iteration (s): 0.20 | learning rate: 2.699E-05 | global batch size: 256 | lm loss: 2.855194E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1295.862 | TFLOPs: 8.25 | +31: iteration 33130/ 37905 | consumed samples: 8481280 | consumed tokens: 17369661440 | elapsed time per iteration (s): 0.26 | learning rate: 2.696E-05 | global batch size: 256 | lm loss: 2.864321E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 971.551 | TFLOPs: 6.19 | +31: iteration 33140/ 37905 | consumed samples: 8483840 | consumed tokens: 17374904320 | elapsed time per iteration (s): 0.20 | learning rate: 2.693E-05 | global batch size: 256 | lm loss: 2.865195E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1288.967 | TFLOPs: 8.21 | +31: iteration 33150/ 37905 | consumed samples: 8486400 | consumed tokens: 17380147200 | elapsed time per iteration (s): 0.23 | learning rate: 2.690E-05 | global batch size: 256 | lm loss: 2.881861E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.540 | TFLOPs: 6.97 | +31: iteration 33160/ 37905 | consumed samples: 8488960 | consumed tokens: 17385390080 | elapsed time per iteration (s): 0.21 | learning rate: 2.687E-05 | global batch size: 256 | lm loss: 2.905320E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.457 | TFLOPs: 7.70 | +31: iteration 33170/ 37905 | consumed samples: 8491520 | consumed tokens: 17390632960 | elapsed time per iteration (s): 0.22 | learning rate: 2.684E-05 | global batch size: 256 | lm loss: 2.890745E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.324 | TFLOPs: 7.47 | +31: iteration 33180/ 37905 | consumed samples: 8494080 | consumed tokens: 17395875840 | elapsed time per iteration (s): 0.24 | learning rate: 2.681E-05 | global batch size: 256 | lm loss: 2.898871E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.091 | TFLOPs: 6.80 | +31: iteration 33190/ 37905 | consumed samples: 8496640 | consumed tokens: 17401118720 | elapsed time per iteration (s): 0.20 | learning rate: 2.679E-05 | global batch size: 256 | lm loss: 2.892387E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1249.441 | TFLOPs: 7.96 | +31: iteration 33200/ 37905 | consumed samples: 8499200 | consumed tokens: 17406361600 | elapsed time per iteration (s): 0.22 | learning rate: 2.676E-05 | global batch size: 256 | lm loss: 2.881575E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.757 | TFLOPs: 7.39 | +31: iteration 33210/ 37905 | consumed samples: 8501760 | consumed tokens: 17411604480 | elapsed time per iteration (s): 0.25 | learning rate: 2.673E-05 | global batch size: 256 | lm loss: 2.899729E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.888 | TFLOPs: 6.45 | +31: iteration 33220/ 37905 | consumed samples: 8504320 | consumed tokens: 17416847360 | elapsed time per iteration (s): 0.23 | learning rate: 2.670E-05 | global batch size: 256 | lm loss: 2.891864E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1136.177 | TFLOPs: 7.24 | +31: iteration 33230/ 37905 | consumed samples: 8506880 | consumed tokens: 17422090240 | elapsed time per iteration (s): 0.23 | learning rate: 2.667E-05 | global batch size: 256 | lm loss: 2.889275E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.623 | TFLOPs: 7.11 | +31: iteration 33240/ 37905 | consumed samples: 8509440 | consumed tokens: 17427333120 | elapsed time per iteration (s): 0.21 | learning rate: 2.664E-05 | global batch size: 256 | lm loss: 2.917789E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.685 | TFLOPs: 7.63 | +31: iteration 33250/ 37905 | consumed samples: 8512000 | consumed tokens: 17432576000 | elapsed time per iteration (s): 0.21 | learning rate: 2.662E-05 | global batch size: 256 | lm loss: 2.900473E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.226 | TFLOPs: 7.74 | +31: iteration 33260/ 37905 | consumed samples: 8514560 | consumed tokens: 17437818880 | elapsed time per iteration (s): 0.24 | learning rate: 2.659E-05 | global batch size: 256 | lm loss: 2.857230E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.213 | TFLOPs: 6.68 | +31: iteration 33270/ 37905 | consumed samples: 8517120 | consumed tokens: 17443061760 | elapsed time per iteration (s): 0.20 | learning rate: 2.656E-05 | global batch size: 256 | lm loss: 2.930087E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.644 | TFLOPs: 8.22 | +31: iteration 33280/ 37905 | consumed samples: 8519680 | consumed tokens: 17448304640 | elapsed time per iteration (s): 0.24 | learning rate: 2.653E-05 | global batch size: 256 | lm loss: 2.941647E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1081.392 | TFLOPs: 6.89 | +31: iteration 33290/ 37905 | consumed samples: 8522240 | consumed tokens: 17453547520 | elapsed time per iteration (s): 0.20 | learning rate: 2.650E-05 | global batch size: 256 | lm loss: 2.918738E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1275.978 | TFLOPs: 8.13 | +31: iteration 33300/ 37905 | consumed samples: 8524800 | consumed tokens: 17458790400 | elapsed time per iteration (s): 0.19 | learning rate: 2.648E-05 | global batch size: 256 | lm loss: 2.864641E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.014 | TFLOPs: 8.36 | +31: iteration 33310/ 37905 | consumed samples: 8527360 | consumed tokens: 17464033280 | elapsed time per iteration (s): 0.21 | learning rate: 2.645E-05 | global batch size: 256 | lm loss: 2.943588E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1235.912 | TFLOPs: 7.87 | +31: iteration 33320/ 37905 | consumed samples: 8529920 | consumed tokens: 17469276160 | elapsed time per iteration (s): 0.22 | learning rate: 2.642E-05 | global batch size: 256 | lm loss: 2.931357E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.569 | TFLOPs: 7.40 | +31: iteration 33330/ 37905 | consumed samples: 8532480 | consumed tokens: 17474519040 | elapsed time per iteration (s): 0.20 | learning rate: 2.639E-05 | global batch size: 256 | lm loss: 2.889563E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1285.142 | TFLOPs: 8.18 | +31: iteration 33340/ 37905 | consumed samples: 8535040 | consumed tokens: 17479761920 | elapsed time per iteration (s): 0.19 | learning rate: 2.637E-05 | global batch size: 256 | lm loss: 2.901958E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1316.654 | TFLOPs: 8.39 | +31: iteration 33350/ 37905 | consumed samples: 8537600 | consumed tokens: 17485004800 | elapsed time per iteration (s): 0.23 | learning rate: 2.634E-05 | global batch size: 256 | lm loss: 2.857482E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1102.829 | TFLOPs: 7.02 | +31: iteration 33360/ 37905 | consumed samples: 8540160 | consumed tokens: 17490247680 | elapsed time per iteration (s): 0.25 | learning rate: 2.631E-05 | global batch size: 256 | lm loss: 2.887570E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.818 | TFLOPs: 6.57 | +31: iteration 33370/ 37905 | consumed samples: 8542720 | consumed tokens: 17495490560 | elapsed time per iteration (s): 0.22 | learning rate: 2.628E-05 | global batch size: 256 | lm loss: 2.897354E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1138.036 | TFLOPs: 7.25 | +31: iteration 33380/ 37905 | consumed samples: 8545280 | consumed tokens: 17500733440 | elapsed time per iteration (s): 0.24 | learning rate: 2.626E-05 | global batch size: 256 | lm loss: 2.923930E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.621 | TFLOPs: 6.83 | +31: iteration 33390/ 37905 | consumed samples: 8547840 | consumed tokens: 17505976320 | elapsed time per iteration (s): 0.23 | learning rate: 2.623E-05 | global batch size: 256 | lm loss: 2.908904E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.236 | TFLOPs: 7.09 | +31: iteration 33400/ 37905 | consumed samples: 8550400 | consumed tokens: 17511219200 | elapsed time per iteration (s): 0.23 | learning rate: 2.620E-05 | global batch size: 256 | lm loss: 2.902224E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.674 | TFLOPs: 7.04 | +31: iteration 33410/ 37905 | consumed samples: 8552960 | consumed tokens: 17516462080 | elapsed time per iteration (s): 0.28 | learning rate: 2.617E-05 | global batch size: 256 | lm loss: 2.910162E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 924.004 | TFLOPs: 5.88 | +31: iteration 33420/ 37905 | consumed samples: 8555520 | consumed tokens: 17521704960 | elapsed time per iteration (s): 0.24 | learning rate: 2.615E-05 | global batch size: 256 | lm loss: 2.855393E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.552 | TFLOPs: 6.75 | +31: iteration 33430/ 37905 | consumed samples: 8558080 | consumed tokens: 17526947840 | elapsed time per iteration (s): 0.23 | learning rate: 2.612E-05 | global batch size: 256 | lm loss: 2.887667E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.036 | TFLOPs: 7.01 | +31: iteration 33440/ 37905 | consumed samples: 8560640 | consumed tokens: 17532190720 | elapsed time per iteration (s): 0.23 | learning rate: 2.609E-05 | global batch size: 256 | lm loss: 2.864071E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.842 | TFLOPs: 7.20 | +31: iteration 33450/ 37905 | consumed samples: 8563200 | consumed tokens: 17537433600 | elapsed time per iteration (s): 0.24 | learning rate: 2.607E-05 | global batch size: 256 | lm loss: 2.935150E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1085.168 | TFLOPs: 6.91 | +31: iteration 33460/ 37905 | consumed samples: 8565760 | consumed tokens: 17542676480 | elapsed time per iteration (s): 0.21 | learning rate: 2.604E-05 | global batch size: 256 | lm loss: 2.920387E+00 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1234.423 | TFLOPs: 7.86 | +31: iteration 33470/ 37905 | consumed samples: 8568320 | consumed tokens: 17547919360 | elapsed time per iteration (s): 0.23 | learning rate: 2.601E-05 | global batch size: 256 | lm loss: 2.885147E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.588 | TFLOPs: 7.17 | +31: iteration 33480/ 37905 | consumed samples: 8570880 | consumed tokens: 17553162240 | elapsed time per iteration (s): 0.20 | learning rate: 2.599E-05 | global batch size: 256 | lm loss: 2.895919E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1292.624 | TFLOPs: 8.23 | +31: iteration 33490/ 37905 | consumed samples: 8573440 | consumed tokens: 17558405120 | elapsed time per iteration (s): 0.26 | learning rate: 2.596E-05 | global batch size: 256 | lm loss: 2.909161E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1001.610 | TFLOPs: 6.38 | +31: iteration 33500/ 37905 | consumed samples: 8576000 | consumed tokens: 17563648000 | elapsed time per iteration (s): 0.22 | learning rate: 2.593E-05 | global batch size: 256 | lm loss: 2.889450E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.840 | TFLOPs: 7.43 | +31: iteration 33510/ 37905 | consumed samples: 8578560 | consumed tokens: 17568890880 | elapsed time per iteration (s): 0.23 | learning rate: 2.591E-05 | global batch size: 256 | lm loss: 2.891774E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.719 | TFLOPs: 7.13 | +31: iteration 33520/ 37905 | consumed samples: 8581120 | consumed tokens: 17574133760 | elapsed time per iteration (s): 0.22 | learning rate: 2.588E-05 | global batch size: 256 | lm loss: 2.879614E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.079 | TFLOPs: 7.42 | +31: iteration 33530/ 37905 | consumed samples: 8583680 | consumed tokens: 17579376640 | elapsed time per iteration (s): 0.21 | learning rate: 2.585E-05 | global batch size: 256 | lm loss: 2.884526E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1244.177 | TFLOPs: 7.92 | +31: iteration 33540/ 37905 | consumed samples: 8586240 | consumed tokens: 17584619520 | elapsed time per iteration (s): 0.21 | learning rate: 2.583E-05 | global batch size: 256 | lm loss: 2.897310E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.542 | TFLOPs: 7.77 | +31: iteration 33550/ 37905 | consumed samples: 8588800 | consumed tokens: 17589862400 | elapsed time per iteration (s): 0.23 | learning rate: 2.580E-05 | global batch size: 256 | lm loss: 2.922285E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.228 | TFLOPs: 6.97 | +31: iteration 33560/ 37905 | consumed samples: 8591360 | consumed tokens: 17595105280 | elapsed time per iteration (s): 0.22 | learning rate: 2.577E-05 | global batch size: 256 | lm loss: 2.882927E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1181.112 | TFLOPs: 7.52 | +31: iteration 33570/ 37905 | consumed samples: 8593920 | consumed tokens: 17600348160 | elapsed time per iteration (s): 0.20 | learning rate: 2.575E-05 | global batch size: 256 | lm loss: 2.905588E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1268.603 | TFLOPs: 8.08 | +31: iteration 33580/ 37905 | consumed samples: 8596480 | consumed tokens: 17605591040 | elapsed time per iteration (s): 0.24 | learning rate: 2.572E-05 | global batch size: 256 | lm loss: 2.893470E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.869 | TFLOPs: 6.74 | +31: iteration 33590/ 37905 | consumed samples: 8599040 | consumed tokens: 17610833920 | elapsed time per iteration (s): 0.22 | learning rate: 2.569E-05 | global batch size: 256 | lm loss: 2.899553E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1151.599 | TFLOPs: 7.33 | +31: iteration 33600/ 37905 | consumed samples: 8601600 | consumed tokens: 17616076800 | elapsed time per iteration (s): 0.21 | learning rate: 2.567E-05 | global batch size: 256 | lm loss: 2.881766E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.683 | TFLOPs: 7.93 | +31: iteration 33610/ 37905 | consumed samples: 8604160 | consumed tokens: 17621319680 | elapsed time per iteration (s): 0.28 | learning rate: 2.564E-05 | global batch size: 256 | lm loss: 2.908530E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 926.006 | TFLOPs: 5.90 | +31: iteration 33620/ 37905 | consumed samples: 8606720 | consumed tokens: 17626562560 | elapsed time per iteration (s): 0.21 | learning rate: 2.562E-05 | global batch size: 256 | lm loss: 2.884946E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.132 | TFLOPs: 7.59 | +31: iteration 33630/ 37905 | consumed samples: 8609280 | consumed tokens: 17631805440 | elapsed time per iteration (s): 0.22 | learning rate: 2.559E-05 | global batch size: 256 | lm loss: 2.874694E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1167.661 | TFLOPs: 7.44 | +31: iteration 33640/ 37905 | consumed samples: 8611840 | consumed tokens: 17637048320 | elapsed time per iteration (s): 0.21 | learning rate: 2.556E-05 | global batch size: 256 | lm loss: 2.912564E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1223.076 | TFLOPs: 7.79 | +31: iteration 33650/ 37905 | consumed samples: 8614400 | consumed tokens: 17642291200 | elapsed time per iteration (s): 0.21 | learning rate: 2.554E-05 | global batch size: 256 | lm loss: 2.905473E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.072 | TFLOPs: 7.90 | +31: iteration 33660/ 37905 | consumed samples: 8616960 | consumed tokens: 17647534080 | elapsed time per iteration (s): 0.23 | learning rate: 2.551E-05 | global batch size: 256 | lm loss: 2.899697E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.222 | TFLOPs: 7.12 | +31: iteration 33670/ 37905 | consumed samples: 8619520 | consumed tokens: 17652776960 | elapsed time per iteration (s): 0.22 | learning rate: 2.549E-05 | global batch size: 256 | lm loss: 2.868641E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.188 | TFLOPs: 7.26 | +31: iteration 33680/ 37905 | consumed samples: 8622080 | consumed tokens: 17658019840 | elapsed time per iteration (s): 0.24 | learning rate: 2.546E-05 | global batch size: 256 | lm loss: 2.884938E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.162 | TFLOPs: 6.80 | +31: iteration 33690/ 37905 | consumed samples: 8624640 | consumed tokens: 17663262720 | elapsed time per iteration (s): 0.22 | learning rate: 2.544E-05 | global batch size: 256 | lm loss: 2.884300E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.144 | TFLOPs: 7.38 | +31: iteration 33700/ 37905 | consumed samples: 8627200 | consumed tokens: 17668505600 | elapsed time per iteration (s): 0.21 | learning rate: 2.541E-05 | global batch size: 256 | lm loss: 2.917724E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.787 | TFLOPs: 7.95 | +31: iteration 33710/ 37905 | consumed samples: 8629760 | consumed tokens: 17673748480 | elapsed time per iteration (s): 0.20 | learning rate: 2.539E-05 | global batch size: 256 | lm loss: 2.937400E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.010 | TFLOPs: 8.07 | +31: iteration 33720/ 37905 | consumed samples: 8632320 | consumed tokens: 17678991360 | elapsed time per iteration (s): 0.26 | learning rate: 2.536E-05 | global batch size: 256 | lm loss: 2.879383E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 975.470 | TFLOPs: 6.21 | +31: iteration 33730/ 37905 | consumed samples: 8634880 | consumed tokens: 17684234240 | elapsed time per iteration (s): 0.20 | learning rate: 2.533E-05 | global batch size: 256 | lm loss: 2.915126E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1267.687 | TFLOPs: 8.07 | +31: iteration 33740/ 37905 | consumed samples: 8637440 | consumed tokens: 17689477120 | elapsed time per iteration (s): 0.23 | learning rate: 2.531E-05 | global batch size: 256 | lm loss: 2.906822E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.252 | TFLOPs: 7.22 | +31: iteration 33750/ 37905 | consumed samples: 8640000 | consumed tokens: 17694720000 | elapsed time per iteration (s): 0.21 | learning rate: 2.528E-05 | global batch size: 256 | lm loss: 2.909024E+00 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.569 | TFLOPs: 7.67 | +31: iteration 33760/ 37905 | consumed samples: 8642560 | consumed tokens: 17699962880 | elapsed time per iteration (s): 0.22 | learning rate: 2.526E-05 | global batch size: 256 | lm loss: 2.947252E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.275 | TFLOPs: 7.45 | +31: iteration 33770/ 37905 | consumed samples: 8645120 | consumed tokens: 17705205760 | elapsed time per iteration (s): 0.24 | learning rate: 2.523E-05 | global batch size: 256 | lm loss: 2.900643E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.788 | TFLOPs: 6.87 | +31: iteration 33780/ 37905 | consumed samples: 8647680 | consumed tokens: 17710448640 | elapsed time per iteration (s): 0.21 | learning rate: 2.521E-05 | global batch size: 256 | lm loss: 2.896762E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.436 | TFLOPs: 7.89 | +31: iteration 33790/ 37905 | consumed samples: 8650240 | consumed tokens: 17715691520 | elapsed time per iteration (s): 0.22 | learning rate: 2.518E-05 | global batch size: 256 | lm loss: 2.916468E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.829 | TFLOPs: 7.44 | +31: iteration 33800/ 37905 | consumed samples: 8652800 | consumed tokens: 17720934400 | elapsed time per iteration (s): 0.23 | learning rate: 2.516E-05 | global batch size: 256 | lm loss: 2.899933E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.339 | TFLOPs: 7.13 | +31: iteration 33810/ 37905 | consumed samples: 8655360 | consumed tokens: 17726177280 | elapsed time per iteration (s): 0.23 | learning rate: 2.513E-05 | global batch size: 256 | lm loss: 2.924535E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.439 | TFLOPs: 7.15 | +31: iteration 33820/ 37905 | consumed samples: 8657920 | consumed tokens: 17731420160 | elapsed time per iteration (s): 0.23 | learning rate: 2.511E-05 | global batch size: 256 | lm loss: 2.903848E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1100.318 | TFLOPs: 7.01 | +31: iteration 33830/ 37905 | consumed samples: 8660480 | consumed tokens: 17736663040 | elapsed time per iteration (s): 0.25 | learning rate: 2.508E-05 | global batch size: 256 | lm loss: 2.926494E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.247 | TFLOPs: 6.58 | +31: iteration 33840/ 37905 | consumed samples: 8663040 | consumed tokens: 17741905920 | elapsed time per iteration (s): 0.21 | learning rate: 2.506E-05 | global batch size: 256 | lm loss: 2.942235E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.387 | TFLOPs: 7.91 | +31: iteration 33850/ 37905 | consumed samples: 8665600 | consumed tokens: 17747148800 | elapsed time per iteration (s): 0.23 | learning rate: 2.504E-05 | global batch size: 256 | lm loss: 2.937241E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.718 | TFLOPs: 7.13 | +31: iteration 33860/ 37905 | consumed samples: 8668160 | consumed tokens: 17752391680 | elapsed time per iteration (s): 0.21 | learning rate: 2.501E-05 | global batch size: 256 | lm loss: 2.871699E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.693 | TFLOPs: 7.79 | +31: iteration 33870/ 37905 | consumed samples: 8670720 | consumed tokens: 17757634560 | elapsed time per iteration (s): 0.22 | learning rate: 2.499E-05 | global batch size: 256 | lm loss: 2.890945E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1147.063 | TFLOPs: 7.31 | +31: iteration 33880/ 37905 | consumed samples: 8673280 | consumed tokens: 17762877440 | elapsed time per iteration (s): 0.23 | learning rate: 2.496E-05 | global batch size: 256 | lm loss: 2.876282E+00 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.580 | TFLOPs: 7.03 | +31: iteration 33890/ 37905 | consumed samples: 8675840 | consumed tokens: 17768120320 | elapsed time per iteration (s): 0.21 | learning rate: 2.494E-05 | global batch size: 256 | lm loss: 2.883154E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.135 | TFLOPs: 7.68 | +31: iteration 33900/ 37905 | consumed samples: 8678400 | consumed tokens: 17773363200 | elapsed time per iteration (s): 0.22 | learning rate: 2.491E-05 | global batch size: 256 | lm loss: 2.884954E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.748 | TFLOPs: 7.49 | +31: iteration 33910/ 37905 | consumed samples: 8680960 | consumed tokens: 17778606080 | elapsed time per iteration (s): 0.22 | learning rate: 2.489E-05 | global batch size: 256 | lm loss: 2.914596E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.991 | TFLOPs: 7.53 | +31: iteration 33920/ 37905 | consumed samples: 8683520 | consumed tokens: 17783848960 | elapsed time per iteration (s): 0.24 | learning rate: 2.486E-05 | global batch size: 256 | lm loss: 2.892567E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.657 | TFLOPs: 6.73 | +31: iteration 33930/ 37905 | consumed samples: 8686080 | consumed tokens: 17789091840 | elapsed time per iteration (s): 0.22 | learning rate: 2.484E-05 | global batch size: 256 | lm loss: 2.866313E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.072 | TFLOPs: 7.48 | +31: iteration 33940/ 37905 | consumed samples: 8688640 | consumed tokens: 17794334720 | elapsed time per iteration (s): 0.21 | learning rate: 2.482E-05 | global batch size: 256 | lm loss: 2.886378E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1213.383 | TFLOPs: 7.73 | +31: iteration 33950/ 37905 | consumed samples: 8691200 | consumed tokens: 17799577600 | elapsed time per iteration (s): 0.23 | learning rate: 2.479E-05 | global batch size: 256 | lm loss: 2.896967E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1115.167 | TFLOPs: 7.10 | +31: iteration 33960/ 37905 | consumed samples: 8693760 | consumed tokens: 17804820480 | elapsed time per iteration (s): 0.21 | learning rate: 2.477E-05 | global batch size: 256 | lm loss: 2.894080E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.485 | TFLOPs: 7.67 | +31: iteration 33970/ 37905 | consumed samples: 8696320 | consumed tokens: 17810063360 | elapsed time per iteration (s): 0.22 | learning rate: 2.474E-05 | global batch size: 256 | lm loss: 2.867069E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.049 | TFLOPs: 7.38 | +31: iteration 33980/ 37905 | consumed samples: 8698880 | consumed tokens: 17815306240 | elapsed time per iteration (s): 0.21 | learning rate: 2.472E-05 | global batch size: 256 | lm loss: 2.891591E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.110 | TFLOPs: 7.68 | +31: iteration 33990/ 37905 | consumed samples: 8701440 | consumed tokens: 17820549120 | elapsed time per iteration (s): 0.21 | learning rate: 2.470E-05 | global batch size: 256 | lm loss: 2.894613E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.310 | TFLOPs: 7.72 | + 0: [2022-11-24 16:15:16,337] [INFO] [logging.py:68:log_dist] [Rank 0] step=34000, skipped=0, lr=[2.4672865261956628e-05, 2.4672865261956628e-05, 2.4672865261956628e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 34000/ 37905 | consumed samples: 8704000 | consumed tokens: 17825792000 | elapsed time per iteration (s): 0.22 | learning rate: 2.467E-05 | global batch size: 256 | lm loss: 2.915209E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1179.183 | TFLOPs: 7.51 | + 0: steps: 34000 loss: 2.9804 iter time (s): 0.220 samples/sec: 1164.162 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 34000 | lm loss value: 2.778610E+00 | lm loss PPL: 1.609663E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 34000 to checkpoints_83m + 0: [2022-11-24 16:15:16,457] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step34000 is begin to save! + 0: [2022-11-24 16:15:16,466] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,550] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,562] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,585] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,597] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,608] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,631] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,632] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,643] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,655] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,666] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:15:16,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:15:16,668] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step34000/mp_rank_00_model_states.pt + 0: [2022-11-24 16:15:16,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:15:16,670] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:15:16,734] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step34000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:15:16,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:15:16,741] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,741] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +21: [2022-11-24 16:15:16,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:15:16,742] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,742] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:15:16,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +20: [2022-11-24 16:15:16,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:15:16,743] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:15:16,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +31: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,744] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +17: [2022-11-24 16:15:16,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 16:15:16,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +27: [2022-11-24 16:15:16,745] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:15:16,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,745] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:15:16,745] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +22: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +23: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +28: [2022-11-24 16:15:16,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,746] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +28: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:15:16,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:15:16,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 4: [2022-11-24 16:15:16,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 2: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:15:16,747] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 16:15:16,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:15:16,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +21: [2022-11-24 16:15:16,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,748] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,748] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +20: [2022-11-24 16:15:16,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,749] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,749] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +27: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,750] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +31: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +17: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +10: [2022-11-24 16:15:16,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +29: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:15:16,751] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:15:16,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +23: [2022-11-24 16:15:16,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:15:16,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,752] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 16:15:16,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,753] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 16:15:16,753] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +28: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:15:16,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:15:16,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 4: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,754] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:15:16,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 2: [2022-11-24 16:15:16,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:15:16,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +20: [2022-11-24 16:15:16,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:15:16,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,755] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,755] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +21: [2022-11-24 16:15:16,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:15:16,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 16:15:16,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:15:16,756] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,756] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +27: [2022-11-24 16:15:16,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,757] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,757] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +31: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +29: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:15:16,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +17: [2022-11-24 16:15:16,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,758] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +17: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,758] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +10: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +23: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,759] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,759] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:15:16,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 16:15:16,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,760] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,760] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 16:15:16,760] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +28: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +28: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:15:16,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:15:16,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 2: [2022-11-24 16:15:16,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 4: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,761] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:15:16,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:15:16,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +21: [2022-11-24 16:15:16,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +19: [2022-11-24 16:15:16,762] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,762] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,763] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:15:16,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +27: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:15:16,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +31: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,764] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +17: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:15:16,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,765] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +29: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +24: [2022-11-24 16:15:16,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +23: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,766] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:15:16,766] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +28: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +22: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,767] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:15:16,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:15:16,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 4: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,768] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:15:16,768] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:15:16,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,769] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 16:15:16,769] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +20: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,770] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:15:16,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +27: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:15:16,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,771] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +31: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +29: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:15:16,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +17: [2022-11-24 16:15:16,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +17: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:15:16,772] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,772] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +24: [2022-11-24 16:15:16,773] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +23: [2022-11-24 16:15:16,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:15:16,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +15: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,774] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +28: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:15:16,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:15:16,775] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 2: [2022-11-24 16:15:16,775] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:15:16,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 4: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +21: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:15:16,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,776] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 16:15:16,776] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +20: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +11: [2022-11-24 16:15:16,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:15:16,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:15:16,777] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,777] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:15:16,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:15:16,778] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +27: [2022-11-24 16:15:16,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:15:16,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +31: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,779] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,779] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +17: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +29: [2022-11-24 16:15:16,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,780] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,780] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +10: [2022-11-24 16:15:16,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 16:15:16,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,781] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:15:16,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:15:16,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:15:16,782] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:15:16,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 4: [2022-11-24 16:15:16,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:15:16,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 2: [2022-11-24 16:15:16,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:15:16,783] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,783] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:15:16,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +28: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +28: [2022-11-24 16:15:16,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,784] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +20: [2022-11-24 16:15:16,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:15:16,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +21: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:15:16,785] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +27: [2022-11-24 16:15:16,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:15:16,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,786] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +25: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 1: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:15:16,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +31: [2022-11-24 16:15:16,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +17: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +29: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:15:16,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,787] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +23: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +10: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +10: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +23: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,788] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +20: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:15:16,788] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +20: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +23: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +16: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +14: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +26: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +31: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +14: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +26: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +27: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +16: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 6: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +24: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 5: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +25: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +10: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 8: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +17: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +10: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 2: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +21: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +21: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +30: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 3: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 4: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +15: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 7: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +29: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +30: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +18: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +12: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +15: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +18: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +12: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +22: [2022-11-24 16:15:16,789] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +13: [2022-11-24 16:15:16,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:15:16,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +13: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:15:16,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +11: [2022-11-24 16:15:16,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 16:15:16,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +19: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +11: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +19: [2022-11-24 16:15:16,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! +28: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:15:16,790] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 16:15:16,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 9: [2022-11-24 16:15:16,791] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:15:16,791] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step34000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:15:16,791] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step34000 is ready now! + 0: successfully saved checkpoint at iteration 34000 to checkpoints_83m +31: time (ms) | save-checkpoint: 340.06 +31: iteration 34010/ 37905 | consumed samples: 8706560 | consumed tokens: 17831034880 | elapsed time per iteration (s): 0.24 | learning rate: 2.465E-05 | global batch size: 256 | lm loss: 2.924304E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.589 | TFLOPs: 6.83 | +31: iteration 34020/ 37905 | consumed samples: 8709120 | consumed tokens: 17836277760 | elapsed time per iteration (s): 0.23 | learning rate: 2.463E-05 | global batch size: 256 | lm loss: 2.910065E+00 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.943 | TFLOPs: 7.00 | +31: iteration 34030/ 37905 | consumed samples: 8711680 | consumed tokens: 17841520640 | elapsed time per iteration (s): 0.21 | learning rate: 2.460E-05 | global batch size: 256 | lm loss: 2.897764E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.002 | TFLOPs: 7.75 | +31: iteration 34040/ 37905 | consumed samples: 8714240 | consumed tokens: 17846763520 | elapsed time per iteration (s): 0.21 | learning rate: 2.458E-05 | global batch size: 256 | lm loss: 2.903401E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1209.784 | TFLOPs: 7.70 | +31: iteration 34050/ 37905 | consumed samples: 8716800 | consumed tokens: 17852006400 | elapsed time per iteration (s): 0.22 | learning rate: 2.455E-05 | global batch size: 256 | lm loss: 2.894654E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1155.619 | TFLOPs: 7.36 | +31: iteration 34060/ 37905 | consumed samples: 8719360 | consumed tokens: 17857249280 | elapsed time per iteration (s): 0.24 | learning rate: 2.453E-05 | global batch size: 256 | lm loss: 2.857295E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.758 | TFLOPs: 6.71 | +31: iteration 34070/ 37905 | consumed samples: 8721920 | consumed tokens: 17862492160 | elapsed time per iteration (s): 0.21 | learning rate: 2.451E-05 | global batch size: 256 | lm loss: 2.869053E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.727 | TFLOPs: 7.72 | +31: iteration 34080/ 37905 | consumed samples: 8724480 | consumed tokens: 17867735040 | elapsed time per iteration (s): 0.22 | learning rate: 2.448E-05 | global batch size: 256 | lm loss: 2.914750E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.827 | TFLOPs: 7.33 | +31: iteration 34090/ 37905 | consumed samples: 8727040 | consumed tokens: 17872977920 | elapsed time per iteration (s): 0.21 | learning rate: 2.446E-05 | global batch size: 256 | lm loss: 2.914916E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.878 | TFLOPs: 7.82 | +31: iteration 34100/ 37905 | consumed samples: 8729600 | consumed tokens: 17878220800 | elapsed time per iteration (s): 0.21 | learning rate: 2.444E-05 | global batch size: 256 | lm loss: 2.891595E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.299 | TFLOPs: 7.89 | +31: iteration 34110/ 37905 | consumed samples: 8732160 | consumed tokens: 17883463680 | elapsed time per iteration (s): 0.22 | learning rate: 2.442E-05 | global batch size: 256 | lm loss: 2.876959E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.880 | TFLOPs: 7.56 | +31: iteration 34120/ 37905 | consumed samples: 8734720 | consumed tokens: 17888706560 | elapsed time per iteration (s): 0.24 | learning rate: 2.439E-05 | global batch size: 256 | lm loss: 2.898058E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1061.198 | TFLOPs: 6.76 | +31: iteration 34130/ 37905 | consumed samples: 8737280 | consumed tokens: 17893949440 | elapsed time per iteration (s): 0.23 | learning rate: 2.437E-05 | global batch size: 256 | lm loss: 2.925102E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.835 | TFLOPs: 7.23 | +31: iteration 34140/ 37905 | consumed samples: 8739840 | consumed tokens: 17899192320 | elapsed time per iteration (s): 0.22 | learning rate: 2.435E-05 | global batch size: 256 | lm loss: 2.852123E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.625 | TFLOPs: 7.51 | +31: iteration 34150/ 37905 | consumed samples: 8742400 | consumed tokens: 17904435200 | elapsed time per iteration (s): 0.25 | learning rate: 2.432E-05 | global batch size: 256 | lm loss: 2.884783E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.669 | TFLOPs: 6.60 | +31: iteration 34160/ 37905 | consumed samples: 8744960 | consumed tokens: 17909678080 | elapsed time per iteration (s): 0.22 | learning rate: 2.430E-05 | global batch size: 256 | lm loss: 2.881621E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.980 | TFLOPs: 7.36 | +31: iteration 34170/ 37905 | consumed samples: 8747520 | consumed tokens: 17914920960 | elapsed time per iteration (s): 0.24 | learning rate: 2.428E-05 | global batch size: 256 | lm loss: 2.893018E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.035 | TFLOPs: 6.74 | +31: iteration 34180/ 37905 | consumed samples: 8750080 | consumed tokens: 17920163840 | elapsed time per iteration (s): 0.22 | learning rate: 2.426E-05 | global batch size: 256 | lm loss: 2.934283E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.088 | TFLOPs: 7.53 | +31: iteration 34190/ 37905 | consumed samples: 8752640 | consumed tokens: 17925406720 | elapsed time per iteration (s): 0.22 | learning rate: 2.423E-05 | global batch size: 256 | lm loss: 2.910217E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.787 | TFLOPs: 7.30 | +31: iteration 34200/ 37905 | consumed samples: 8755200 | consumed tokens: 17930649600 | elapsed time per iteration (s): 0.21 | learning rate: 2.421E-05 | global batch size: 256 | lm loss: 2.864434E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.552 | TFLOPs: 7.77 | +31: iteration 34210/ 37905 | consumed samples: 8757760 | consumed tokens: 17935892480 | elapsed time per iteration (s): 0.21 | learning rate: 2.419E-05 | global batch size: 256 | lm loss: 2.881502E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.927 | TFLOPs: 7.88 | +31: iteration 34220/ 37905 | consumed samples: 8760320 | consumed tokens: 17941135360 | elapsed time per iteration (s): 0.20 | learning rate: 2.417E-05 | global batch size: 256 | lm loss: 2.900613E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.924 | TFLOPs: 8.01 | +31: iteration 34230/ 37905 | consumed samples: 8762880 | consumed tokens: 17946378240 | elapsed time per iteration (s): 0.26 | learning rate: 2.414E-05 | global batch size: 256 | lm loss: 2.859889E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 982.353 | TFLOPs: 6.26 | +31: iteration 34240/ 37905 | consumed samples: 8765440 | consumed tokens: 17951621120 | elapsed time per iteration (s): 0.26 | learning rate: 2.412E-05 | global batch size: 256 | lm loss: 2.877029E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 994.384 | TFLOPs: 6.33 | +31: iteration 34250/ 37905 | consumed samples: 8768000 | consumed tokens: 17956864000 | elapsed time per iteration (s): 0.24 | learning rate: 2.410E-05 | global batch size: 256 | lm loss: 2.891077E+00 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.314 | TFLOPs: 6.68 | +31: iteration 34260/ 37905 | consumed samples: 8770560 | consumed tokens: 17962106880 | elapsed time per iteration (s): 0.23 | learning rate: 2.408E-05 | global batch size: 256 | lm loss: 2.891375E+00 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.385 | TFLOPs: 7.15 | +31: iteration 34270/ 37905 | consumed samples: 8773120 | consumed tokens: 17967349760 | elapsed time per iteration (s): 0.21 | learning rate: 2.405E-05 | global batch size: 256 | lm loss: 2.913173E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.091 | TFLOPs: 7.94 | +31: iteration 34280/ 37905 | consumed samples: 8775680 | consumed tokens: 17972592640 | elapsed time per iteration (s): 0.25 | learning rate: 2.403E-05 | global batch size: 256 | lm loss: 2.909537E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1004.430 | TFLOPs: 6.40 | +31: iteration 34290/ 37905 | consumed samples: 8778240 | consumed tokens: 17977835520 | elapsed time per iteration (s): 0.25 | learning rate: 2.401E-05 | global batch size: 256 | lm loss: 2.926922E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.732 | TFLOPs: 6.60 | +31: iteration 34300/ 37905 | consumed samples: 8780800 | consumed tokens: 17983078400 | elapsed time per iteration (s): 0.21 | learning rate: 2.399E-05 | global batch size: 256 | lm loss: 2.919790E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.017 | TFLOPs: 7.60 | +31: iteration 34310/ 37905 | consumed samples: 8783360 | consumed tokens: 17988321280 | elapsed time per iteration (s): 0.20 | learning rate: 2.397E-05 | global batch size: 256 | lm loss: 2.891870E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.541 | TFLOPs: 8.00 | +31: iteration 34320/ 37905 | consumed samples: 8785920 | consumed tokens: 17993564160 | elapsed time per iteration (s): 0.20 | learning rate: 2.394E-05 | global batch size: 256 | lm loss: 2.942222E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1311.240 | TFLOPs: 8.35 | +31: iteration 34330/ 37905 | consumed samples: 8788480 | consumed tokens: 17998807040 | elapsed time per iteration (s): 0.22 | learning rate: 2.392E-05 | global batch size: 256 | lm loss: 2.919145E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.645 | TFLOPs: 7.47 | +31: iteration 34340/ 37905 | consumed samples: 8791040 | consumed tokens: 18004049920 | elapsed time per iteration (s): 0.21 | learning rate: 2.390E-05 | global batch size: 256 | lm loss: 2.868661E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1224.842 | TFLOPs: 7.80 | +31: iteration 34350/ 37905 | consumed samples: 8793600 | consumed tokens: 18009292800 | elapsed time per iteration (s): 0.22 | learning rate: 2.388E-05 | global batch size: 256 | lm loss: 2.868698E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1143.511 | TFLOPs: 7.28 | +31: iteration 34360/ 37905 | consumed samples: 8796160 | consumed tokens: 18014535680 | elapsed time per iteration (s): 0.22 | learning rate: 2.386E-05 | global batch size: 256 | lm loss: 2.854281E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1170.210 | TFLOPs: 7.45 | +31: iteration 34370/ 37905 | consumed samples: 8798720 | consumed tokens: 18019778560 | elapsed time per iteration (s): 0.26 | learning rate: 2.384E-05 | global batch size: 256 | lm loss: 2.916276E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1003.278 | TFLOPs: 6.39 | +31: iteration 34380/ 37905 | consumed samples: 8801280 | consumed tokens: 18025021440 | elapsed time per iteration (s): 0.22 | learning rate: 2.381E-05 | global batch size: 256 | lm loss: 2.926926E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.537 | TFLOPs: 7.45 | +31: iteration 34390/ 37905 | consumed samples: 8803840 | consumed tokens: 18030264320 | elapsed time per iteration (s): 0.22 | learning rate: 2.379E-05 | global batch size: 256 | lm loss: 2.865707E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.581 | TFLOPs: 7.26 | +31: iteration 34400/ 37905 | consumed samples: 8806400 | consumed tokens: 18035507200 | elapsed time per iteration (s): 0.20 | learning rate: 2.377E-05 | global batch size: 256 | lm loss: 2.922623E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1291.619 | TFLOPs: 8.23 | +31: iteration 34410/ 37905 | consumed samples: 8808960 | consumed tokens: 18040750080 | elapsed time per iteration (s): 0.21 | learning rate: 2.375E-05 | global batch size: 256 | lm loss: 2.917940E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.792 | TFLOPs: 7.95 | +31: iteration 34420/ 37905 | consumed samples: 8811520 | consumed tokens: 18045992960 | elapsed time per iteration (s): 0.23 | learning rate: 2.373E-05 | global batch size: 256 | lm loss: 2.908664E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.601 | TFLOPs: 7.14 | +31: iteration 34430/ 37905 | consumed samples: 8814080 | consumed tokens: 18051235840 | elapsed time per iteration (s): 0.21 | learning rate: 2.371E-05 | global batch size: 256 | lm loss: 2.918176E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.930 | TFLOPs: 7.72 | +31: iteration 34440/ 37905 | consumed samples: 8816640 | consumed tokens: 18056478720 | elapsed time per iteration (s): 0.21 | learning rate: 2.369E-05 | global batch size: 256 | lm loss: 2.908861E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1236.850 | TFLOPs: 7.88 | +31: iteration 34450/ 37905 | consumed samples: 8819200 | consumed tokens: 18061721600 | elapsed time per iteration (s): 0.22 | learning rate: 2.366E-05 | global batch size: 256 | lm loss: 2.903921E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.682 | TFLOPs: 7.45 | +31: iteration 34460/ 37905 | consumed samples: 8821760 | consumed tokens: 18066964480 | elapsed time per iteration (s): 0.21 | learning rate: 2.364E-05 | global batch size: 256 | lm loss: 2.865333E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.971 | TFLOPs: 7.60 | +31: iteration 34470/ 37905 | consumed samples: 8824320 | consumed tokens: 18072207360 | elapsed time per iteration (s): 0.21 | learning rate: 2.362E-05 | global batch size: 256 | lm loss: 2.867150E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1225.250 | TFLOPs: 7.80 | +31: iteration 34480/ 37905 | consumed samples: 8826880 | consumed tokens: 18077450240 | elapsed time per iteration (s): 0.23 | learning rate: 2.360E-05 | global batch size: 256 | lm loss: 2.865060E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.826 | TFLOPs: 7.21 | +31: iteration 34490/ 37905 | consumed samples: 8829440 | consumed tokens: 18082693120 | elapsed time per iteration (s): 0.23 | learning rate: 2.358E-05 | global batch size: 256 | lm loss: 2.894559E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.038 | TFLOPs: 7.15 | +31: iteration 34500/ 37905 | consumed samples: 8832000 | consumed tokens: 18087936000 | elapsed time per iteration (s): 0.22 | learning rate: 2.356E-05 | global batch size: 256 | lm loss: 2.848295E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.876 | TFLOPs: 7.37 | +31: iteration 34510/ 37905 | consumed samples: 8834560 | consumed tokens: 18093178880 | elapsed time per iteration (s): 0.21 | learning rate: 2.354E-05 | global batch size: 256 | lm loss: 2.865258E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.118 | TFLOPs: 7.68 | +31: iteration 34520/ 37905 | consumed samples: 8837120 | consumed tokens: 18098421760 | elapsed time per iteration (s): 0.23 | learning rate: 2.352E-05 | global batch size: 256 | lm loss: 2.880354E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.264 | TFLOPs: 7.22 | +31: iteration 34530/ 37905 | consumed samples: 8839680 | consumed tokens: 18103664640 | elapsed time per iteration (s): 0.22 | learning rate: 2.350E-05 | global batch size: 256 | lm loss: 2.903147E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.757 | TFLOPs: 7.42 | +31: iteration 34540/ 37905 | consumed samples: 8842240 | consumed tokens: 18108907520 | elapsed time per iteration (s): 0.22 | learning rate: 2.348E-05 | global batch size: 256 | lm loss: 2.873083E+00 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.063 | TFLOPs: 7.42 | +31: iteration 34550/ 37905 | consumed samples: 8844800 | consumed tokens: 18114150400 | elapsed time per iteration (s): 0.22 | learning rate: 2.346E-05 | global batch size: 256 | lm loss: 2.918823E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.549 | TFLOPs: 7.30 | +31: iteration 34560/ 37905 | consumed samples: 8847360 | consumed tokens: 18119393280 | elapsed time per iteration (s): 0.21 | learning rate: 2.344E-05 | global batch size: 256 | lm loss: 2.860411E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1219.837 | TFLOPs: 7.77 | +31: iteration 34570/ 37905 | consumed samples: 8849920 | consumed tokens: 18124636160 | elapsed time per iteration (s): 0.22 | learning rate: 2.342E-05 | global batch size: 256 | lm loss: 2.890794E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.168 | TFLOPs: 7.56 | +31: iteration 34580/ 37905 | consumed samples: 8852480 | consumed tokens: 18129879040 | elapsed time per iteration (s): 0.21 | learning rate: 2.340E-05 | global batch size: 256 | lm loss: 2.920187E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1208.108 | TFLOPs: 7.69 | +31: iteration 34590/ 37905 | consumed samples: 8855040 | consumed tokens: 18135121920 | elapsed time per iteration (s): 0.25 | learning rate: 2.338E-05 | global batch size: 256 | lm loss: 2.853999E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.933 | TFLOPs: 6.48 | +31: iteration 34600/ 37905 | consumed samples: 8857600 | consumed tokens: 18140364800 | elapsed time per iteration (s): 0.25 | learning rate: 2.336E-05 | global batch size: 256 | lm loss: 2.885036E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.856 | TFLOPs: 6.62 | +31: iteration 34610/ 37905 | consumed samples: 8860160 | consumed tokens: 18145607680 | elapsed time per iteration (s): 0.22 | learning rate: 2.334E-05 | global batch size: 256 | lm loss: 2.825136E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1186.621 | TFLOPs: 7.56 | +31: iteration 34620/ 37905 | consumed samples: 8862720 | consumed tokens: 18150850560 | elapsed time per iteration (s): 0.22 | learning rate: 2.332E-05 | global batch size: 256 | lm loss: 2.872995E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.728 | TFLOPs: 7.33 | +31: iteration 34630/ 37905 | consumed samples: 8865280 | consumed tokens: 18156093440 | elapsed time per iteration (s): 0.22 | learning rate: 2.330E-05 | global batch size: 256 | lm loss: 2.883798E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1155.551 | TFLOPs: 7.36 | +31: iteration 34640/ 37905 | consumed samples: 8867840 | consumed tokens: 18161336320 | elapsed time per iteration (s): 0.21 | learning rate: 2.328E-05 | global batch size: 256 | lm loss: 2.900999E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.758 | TFLOPs: 7.92 | +31: iteration 34650/ 37905 | consumed samples: 8870400 | consumed tokens: 18166579200 | elapsed time per iteration (s): 0.25 | learning rate: 2.326E-05 | global batch size: 256 | lm loss: 2.900274E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1017.155 | TFLOPs: 6.48 | +31: iteration 34660/ 37905 | consumed samples: 8872960 | consumed tokens: 18171822080 | elapsed time per iteration (s): 0.21 | learning rate: 2.324E-05 | global batch size: 256 | lm loss: 2.887251E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1193.507 | TFLOPs: 7.60 | +31: iteration 34670/ 37905 | consumed samples: 8875520 | consumed tokens: 18177064960 | elapsed time per iteration (s): 0.22 | learning rate: 2.322E-05 | global batch size: 256 | lm loss: 2.901776E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.869 | TFLOPs: 7.35 | +31: iteration 34680/ 37905 | consumed samples: 8878080 | consumed tokens: 18182307840 | elapsed time per iteration (s): 0.20 | learning rate: 2.320E-05 | global batch size: 256 | lm loss: 2.896536E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1265.543 | TFLOPs: 8.06 | +31: iteration 34690/ 37905 | consumed samples: 8880640 | consumed tokens: 18187550720 | elapsed time per iteration (s): 0.23 | learning rate: 2.318E-05 | global batch size: 256 | lm loss: 2.908218E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.794 | TFLOPs: 7.20 | +31: iteration 34700/ 37905 | consumed samples: 8883200 | consumed tokens: 18192793600 | elapsed time per iteration (s): 0.25 | learning rate: 2.316E-05 | global batch size: 256 | lm loss: 2.879588E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1005.627 | TFLOPs: 6.40 | +31: iteration 34710/ 37905 | consumed samples: 8885760 | consumed tokens: 18198036480 | elapsed time per iteration (s): 0.23 | learning rate: 2.314E-05 | global batch size: 256 | lm loss: 2.890514E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.618 | TFLOPs: 7.23 | +31: iteration 34720/ 37905 | consumed samples: 8888320 | consumed tokens: 18203279360 | elapsed time per iteration (s): 0.23 | learning rate: 2.312E-05 | global batch size: 256 | lm loss: 2.905404E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1133.106 | TFLOPs: 7.22 | +31: iteration 34730/ 37905 | consumed samples: 8890880 | consumed tokens: 18208522240 | elapsed time per iteration (s): 0.26 | learning rate: 2.310E-05 | global batch size: 256 | lm loss: 2.909877E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 977.194 | TFLOPs: 6.22 | +31: iteration 34740/ 37905 | consumed samples: 8893440 | consumed tokens: 18213765120 | elapsed time per iteration (s): 0.21 | learning rate: 2.308E-05 | global batch size: 256 | lm loss: 2.905561E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1222.281 | TFLOPs: 7.78 | +31: iteration 34750/ 37905 | consumed samples: 8896000 | consumed tokens: 18219008000 | elapsed time per iteration (s): 0.25 | learning rate: 2.306E-05 | global batch size: 256 | lm loss: 2.896425E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1044.366 | TFLOPs: 6.65 | +31: iteration 34760/ 37905 | consumed samples: 8898560 | consumed tokens: 18224250880 | elapsed time per iteration (s): 0.23 | learning rate: 2.304E-05 | global batch size: 256 | lm loss: 2.884227E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1099.227 | TFLOPs: 7.00 | +31: iteration 34770/ 37905 | consumed samples: 8901120 | consumed tokens: 18229493760 | elapsed time per iteration (s): 0.22 | learning rate: 2.302E-05 | global batch size: 256 | lm loss: 2.875917E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.772 | TFLOPs: 7.42 | +31: iteration 34780/ 37905 | consumed samples: 8903680 | consumed tokens: 18234736640 | elapsed time per iteration (s): 0.21 | learning rate: 2.300E-05 | global batch size: 256 | lm loss: 2.857503E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1237.411 | TFLOPs: 7.88 | +31: iteration 34790/ 37905 | consumed samples: 8906240 | consumed tokens: 18239979520 | elapsed time per iteration (s): 0.22 | learning rate: 2.298E-05 | global batch size: 256 | lm loss: 2.880399E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1174.994 | TFLOPs: 7.48 | +31: iteration 34800/ 37905 | consumed samples: 8908800 | consumed tokens: 18245222400 | elapsed time per iteration (s): 0.24 | learning rate: 2.296E-05 | global batch size: 256 | lm loss: 2.884816E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1083.811 | TFLOPs: 6.90 | +31: iteration 34810/ 37905 | consumed samples: 8911360 | consumed tokens: 18250465280 | elapsed time per iteration (s): 0.21 | learning rate: 2.294E-05 | global batch size: 256 | lm loss: 2.897262E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1228.420 | TFLOPs: 7.82 | +31: iteration 34820/ 37905 | consumed samples: 8913920 | consumed tokens: 18255708160 | elapsed time per iteration (s): 0.25 | learning rate: 2.293E-05 | global batch size: 256 | lm loss: 2.858164E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.918 | TFLOPs: 6.56 | +31: iteration 34830/ 37905 | consumed samples: 8916480 | consumed tokens: 18260951040 | elapsed time per iteration (s): 0.23 | learning rate: 2.291E-05 | global batch size: 256 | lm loss: 2.867881E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.844 | TFLOPs: 7.07 | +31: iteration 34840/ 37905 | consumed samples: 8919040 | consumed tokens: 18266193920 | elapsed time per iteration (s): 0.22 | learning rate: 2.289E-05 | global batch size: 256 | lm loss: 2.891921E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1157.968 | TFLOPs: 7.37 | +31: iteration 34850/ 37905 | consumed samples: 8921600 | consumed tokens: 18271436800 | elapsed time per iteration (s): 0.22 | learning rate: 2.287E-05 | global batch size: 256 | lm loss: 2.911863E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1172.051 | TFLOPs: 7.46 | +31: iteration 34860/ 37905 | consumed samples: 8924160 | consumed tokens: 18276679680 | elapsed time per iteration (s): 0.21 | learning rate: 2.285E-05 | global batch size: 256 | lm loss: 2.889437E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1241.616 | TFLOPs: 7.91 | +31: iteration 34870/ 37905 | consumed samples: 8926720 | consumed tokens: 18281922560 | elapsed time per iteration (s): 0.26 | learning rate: 2.283E-05 | global batch size: 256 | lm loss: 2.943791E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.896 | TFLOPs: 6.37 | +31: iteration 34880/ 37905 | consumed samples: 8929280 | consumed tokens: 18287165440 | elapsed time per iteration (s): 0.21 | learning rate: 2.281E-05 | global batch size: 256 | lm loss: 2.866397E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.472 | TFLOPs: 7.89 | +31: iteration 34890/ 37905 | consumed samples: 8931840 | consumed tokens: 18292408320 | elapsed time per iteration (s): 0.22 | learning rate: 2.280E-05 | global batch size: 256 | lm loss: 2.929053E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.372 | TFLOPs: 7.49 | +31: iteration 34900/ 37905 | consumed samples: 8934400 | consumed tokens: 18297651200 | elapsed time per iteration (s): 0.23 | learning rate: 2.278E-05 | global batch size: 256 | lm loss: 2.919683E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.331 | TFLOPs: 7.07 | +31: iteration 34910/ 37905 | consumed samples: 8936960 | consumed tokens: 18302894080 | elapsed time per iteration (s): 0.20 | learning rate: 2.276E-05 | global batch size: 256 | lm loss: 2.907366E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1264.733 | TFLOPs: 8.05 | +31: iteration 34920/ 37905 | consumed samples: 8939520 | consumed tokens: 18308136960 | elapsed time per iteration (s): 0.24 | learning rate: 2.274E-05 | global batch size: 256 | lm loss: 2.878535E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.840 | TFLOPs: 6.81 | +31: iteration 34930/ 37905 | consumed samples: 8942080 | consumed tokens: 18313379840 | elapsed time per iteration (s): 0.23 | learning rate: 2.272E-05 | global batch size: 256 | lm loss: 2.903242E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.973 | TFLOPs: 6.95 | +31: iteration 34940/ 37905 | consumed samples: 8944640 | consumed tokens: 18318622720 | elapsed time per iteration (s): 0.24 | learning rate: 2.270E-05 | global batch size: 256 | lm loss: 2.885074E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.534 | TFLOPs: 6.80 | +31: iteration 34950/ 37905 | consumed samples: 8947200 | consumed tokens: 18323865600 | elapsed time per iteration (s): 0.23 | learning rate: 2.269E-05 | global batch size: 256 | lm loss: 2.892489E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.346 | TFLOPs: 7.07 | +31: iteration 34960/ 37905 | consumed samples: 8949760 | consumed tokens: 18329108480 | elapsed time per iteration (s): 0.26 | learning rate: 2.267E-05 | global batch size: 256 | lm loss: 2.884187E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 970.202 | TFLOPs: 6.18 | +31: iteration 34970/ 37905 | consumed samples: 8952320 | consumed tokens: 18334351360 | elapsed time per iteration (s): 0.22 | learning rate: 2.265E-05 | global batch size: 256 | lm loss: 2.923198E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1152.344 | TFLOPs: 7.34 | +31: iteration 34980/ 37905 | consumed samples: 8954880 | consumed tokens: 18339594240 | elapsed time per iteration (s): 0.19 | learning rate: 2.263E-05 | global batch size: 256 | lm loss: 2.917002E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1357.238 | TFLOPs: 8.64 | +31: iteration 34990/ 37905 | consumed samples: 8957440 | consumed tokens: 18344837120 | elapsed time per iteration (s): 0.21 | learning rate: 2.261E-05 | global batch size: 256 | lm loss: 2.927952E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1215.718 | TFLOPs: 7.74 | +31: iteration 35000/ 37905 | consumed samples: 8960000 | consumed tokens: 18350080000 | elapsed time per iteration (s): 0.22 | learning rate: 2.260E-05 | global batch size: 256 | lm loss: 2.917243E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.522 | TFLOPs: 7.41 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 35000 | lm loss value: 2.865076E+00 | lm loss PPL: 1.755039E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 35000 to checkpoints_83m + 0: [2022-11-24 16:19:00,194] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step35000 is begin to save! + 0: [2022-11-24 16:19:00,202] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,280] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,292] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,304] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,304] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,316] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,327] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,339] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,350] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,361] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,362] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,373] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,396] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:19:00,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:19:00,397] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step35000/mp_rank_00_model_states.pt + 0: [2022-11-24 16:19:00,397] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:19:00,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:19:00,463] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step35000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:19:00,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,470] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 16:19:00,470] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:19:00,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 3: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,471] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:19:00,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:19:00,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:19:00,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:19:00,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +29: [2022-11-24 16:19:00,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,472] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,472] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +19: [2022-11-24 16:19:00,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:19:00,473] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +28: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +14: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:19:00,474] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 7: [2022-11-24 16:19:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +10: [2022-11-24 16:19:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +10: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +20: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,475] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:19:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 3: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,476] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:19:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +30: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:19:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,477] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,477] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 2: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +29: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +29: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +24: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +24: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:19:00,478] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 16:19:00,478] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +28: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:19:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:19:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +14: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:19:00,479] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +27: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +27: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +26: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +26: [2022-11-24 16:19:00,480] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +26: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 7: [2022-11-24 16:19:00,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 5: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +10: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +20: [2022-11-24 16:19:00,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,481] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,481] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:19:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:19:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +12: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +12: [2022-11-24 16:19:00,482] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,482] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:19:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:19:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +29: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:19:00,483] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,483] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:19:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:19:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +30: [2022-11-24 16:19:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +19: [2022-11-24 16:19:00,484] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 2: [2022-11-24 16:19:00,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 1: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,485] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +28: [2022-11-24 16:19:00,485] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:19:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:19:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +14: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,486] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 5: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 7: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:19:00,487] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +10: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +10: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +20: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:19:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:19:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:19:00,488] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,488] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 3: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:19:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:19:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:19:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +12: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:19:00,489] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,489] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +29: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:19:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 2: [2022-11-24 16:19:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +19: [2022-11-24 16:19:00,490] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +11: [2022-11-24 16:19:00,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +24: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +30: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:19:00,491] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 1: [2022-11-24 16:19:00,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +27: [2022-11-24 16:19:00,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:19:00,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +27: [2022-11-24 16:19:00,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:19:00,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,492] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 16:19:00,492] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:19:00,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +14: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +26: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:19:00,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:19:00,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,493] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 16:19:00,493] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 5: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +20: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +10: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:19:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +25: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,494] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +10: [2022-11-24 16:19:00,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,495] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 3: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +29: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +12: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +29: [2022-11-24 16:19:00,496] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 16:19:00,496] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +19: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +19: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +30: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +24: [2022-11-24 16:19:00,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,497] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +30: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:19:00,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 1: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:19:00,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +27: [2022-11-24 16:19:00,498] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,498] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:19:00,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +28: [2022-11-24 16:19:00,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +14: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:19:00,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +31: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +14: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +26: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:19:00,499] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 7: [2022-11-24 16:19:00,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:19:00,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 5: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:19:00,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +20: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,500] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +25: [2022-11-24 16:19:00,500] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +10: [2022-11-24 16:19:00,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +10: [2022-11-24 16:19:00,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:19:00,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,501] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:19:00,501] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:19:00,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:19:00,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +12: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,502] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +29: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,503] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,503] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:19:00,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 2: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +24: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 3: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:19:00,504] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,504] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 1: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +27: [2022-11-24 16:19:00,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +28: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:19:00,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +14: [2022-11-24 16:19:00,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,505] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:19:00,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +31: [2022-11-24 16:19:00,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:19:00,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 5: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 7: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +25: [2022-11-24 16:19:00,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:19:00,506] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:19:00,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +10: [2022-11-24 16:19:00,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,507] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +20: [2022-11-24 16:19:00,507] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,507] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 3: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:19:00,508] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:19:00,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +12: [2022-11-24 16:19:00,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:19:00,509] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 16:19:00,509] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +29: [2022-11-24 16:19:00,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +11: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 2: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:19:00,510] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:19:00,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +30: [2022-11-24 16:19:00,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:19:00,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +24: [2022-11-24 16:19:00,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,511] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,511] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 1: [2022-11-24 16:19:00,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +27: [2022-11-24 16:19:00,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +27: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +28: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:19:00,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,512] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:19:00,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +26: [2022-11-24 16:19:00,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:19:00,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:19:00,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:19:00,513] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 16:19:00,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 5: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +31: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +25: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 1: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 8: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +17: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +17: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 5: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +16: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +28: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +16: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +15: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 2: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 3: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +28: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +26: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +29: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +27: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 9: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +27: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:19:00,514] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +14: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +13: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +20: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +27: [2022-11-24 16:19:00,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +25: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +19: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 6: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +13: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +26: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +29: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +25: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +10: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +25: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +30: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 4: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +30: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +18: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +25: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +22: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +18: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +22: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +11: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,515] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +23: [2022-11-24 16:19:00,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +24: [2022-11-24 16:19:00,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:19:00,516] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 16:19:00,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 7: [2022-11-24 16:19:00,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:19:00,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:19:00,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! +21: [2022-11-24 16:19:00,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:19:00,517] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step35000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 16:19:00,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step35000 is ready now! + 0: successfully saved checkpoint at iteration 35000 to checkpoints_83m +31: time (ms) | save-checkpoint: 326.41 +31: iteration 35010/ 37905 | consumed samples: 8962560 | consumed tokens: 18355322880 | elapsed time per iteration (s): 0.29 | learning rate: 2.258E-05 | global batch size: 256 | lm loss: 2.909166E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 889.865 | TFLOPs: 5.67 | +31: iteration 35020/ 37905 | consumed samples: 8965120 | consumed tokens: 18360565760 | elapsed time per iteration (s): 0.22 | learning rate: 2.256E-05 | global batch size: 256 | lm loss: 2.914087E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.608 | TFLOPs: 7.27 | +31: iteration 35030/ 37905 | consumed samples: 8967680 | consumed tokens: 18365808640 | elapsed time per iteration (s): 0.25 | learning rate: 2.254E-05 | global batch size: 256 | lm loss: 2.910494E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1004.194 | TFLOPs: 6.40 | +31: iteration 35040/ 37905 | consumed samples: 8970240 | consumed tokens: 18371051520 | elapsed time per iteration (s): 0.21 | learning rate: 2.253E-05 | global batch size: 256 | lm loss: 2.887778E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.726 | TFLOPs: 7.69 | +31: iteration 35050/ 37905 | consumed samples: 8972800 | consumed tokens: 18376294400 | elapsed time per iteration (s): 0.20 | learning rate: 2.251E-05 | global batch size: 256 | lm loss: 2.923145E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1268.583 | TFLOPs: 8.08 | +31: iteration 35060/ 37905 | consumed samples: 8975360 | consumed tokens: 18381537280 | elapsed time per iteration (s): 0.22 | learning rate: 2.249E-05 | global batch size: 256 | lm loss: 2.875469E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1149.226 | TFLOPs: 7.32 | +31: iteration 35070/ 37905 | consumed samples: 8977920 | consumed tokens: 18386780160 | elapsed time per iteration (s): 0.21 | learning rate: 2.247E-05 | global batch size: 256 | lm loss: 2.906114E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1238.307 | TFLOPs: 7.89 | +31: iteration 35080/ 37905 | consumed samples: 8980480 | consumed tokens: 18392023040 | elapsed time per iteration (s): 0.21 | learning rate: 2.246E-05 | global batch size: 256 | lm loss: 2.856707E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.091 | TFLOPs: 7.92 | +31: iteration 35090/ 37905 | consumed samples: 8983040 | consumed tokens: 18397265920 | elapsed time per iteration (s): 0.21 | learning rate: 2.244E-05 | global batch size: 256 | lm loss: 2.885803E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.921 | TFLOPs: 7.62 | +31: iteration 35100/ 37905 | consumed samples: 8985600 | consumed tokens: 18402508800 | elapsed time per iteration (s): 0.26 | learning rate: 2.242E-05 | global batch size: 256 | lm loss: 2.862649E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 970.451 | TFLOPs: 6.18 | +31: iteration 35110/ 37905 | consumed samples: 8988160 | consumed tokens: 18407751680 | elapsed time per iteration (s): 0.20 | learning rate: 2.240E-05 | global batch size: 256 | lm loss: 2.871316E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.800 | TFLOPs: 8.00 | +31: iteration 35120/ 37905 | consumed samples: 8990720 | consumed tokens: 18412994560 | elapsed time per iteration (s): 0.24 | learning rate: 2.239E-05 | global batch size: 256 | lm loss: 2.886692E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.102 | TFLOPs: 6.73 | +31: iteration 35130/ 37905 | consumed samples: 8993280 | consumed tokens: 18418237440 | elapsed time per iteration (s): 0.25 | learning rate: 2.237E-05 | global batch size: 256 | lm loss: 2.902245E+00 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1009.291 | TFLOPs: 6.43 | +31: iteration 35140/ 37905 | consumed samples: 8995840 | consumed tokens: 18423480320 | elapsed time per iteration (s): 0.23 | learning rate: 2.235E-05 | global batch size: 256 | lm loss: 2.906850E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1093.332 | TFLOPs: 6.96 | +31: iteration 35150/ 37905 | consumed samples: 8998400 | consumed tokens: 18428723200 | elapsed time per iteration (s): 0.21 | learning rate: 2.234E-05 | global batch size: 256 | lm loss: 2.895746E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1218.765 | TFLOPs: 7.76 | +31: iteration 35160/ 37905 | consumed samples: 9000960 | consumed tokens: 18433966080 | elapsed time per iteration (s): 0.24 | learning rate: 2.232E-05 | global batch size: 256 | lm loss: 2.885364E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1088.047 | TFLOPs: 6.93 | +31: iteration 35170/ 37905 | consumed samples: 9003520 | consumed tokens: 18439208960 | elapsed time per iteration (s): 0.20 | learning rate: 2.230E-05 | global batch size: 256 | lm loss: 2.867986E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1282.384 | TFLOPs: 8.17 | +31: iteration 35180/ 37905 | consumed samples: 9006080 | consumed tokens: 18444451840 | elapsed time per iteration (s): 0.21 | learning rate: 2.229E-05 | global batch size: 256 | lm loss: 2.890084E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1211.509 | TFLOPs: 7.72 | +31: iteration 35190/ 37905 | consumed samples: 9008640 | consumed tokens: 18449694720 | elapsed time per iteration (s): 0.20 | learning rate: 2.227E-05 | global batch size: 256 | lm loss: 2.909993E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1255.206 | TFLOPs: 7.99 | +31: iteration 35200/ 37905 | consumed samples: 9011200 | consumed tokens: 18454937600 | elapsed time per iteration (s): 0.22 | learning rate: 2.225E-05 | global batch size: 256 | lm loss: 2.913403E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1166.044 | TFLOPs: 7.43 | +31: iteration 35210/ 37905 | consumed samples: 9013760 | consumed tokens: 18460180480 | elapsed time per iteration (s): 0.20 | learning rate: 2.224E-05 | global batch size: 256 | lm loss: 2.892404E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1252.150 | TFLOPs: 7.97 | +31: iteration 35220/ 37905 | consumed samples: 9016320 | consumed tokens: 18465423360 | elapsed time per iteration (s): 0.21 | learning rate: 2.222E-05 | global batch size: 256 | lm loss: 2.896226E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.007 | TFLOPs: 7.68 | +31: iteration 35230/ 37905 | consumed samples: 9018880 | consumed tokens: 18470666240 | elapsed time per iteration (s): 0.26 | learning rate: 2.220E-05 | global batch size: 256 | lm loss: 2.895329E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.796 | TFLOPs: 6.32 | +31: iteration 35240/ 37905 | consumed samples: 9021440 | consumed tokens: 18475909120 | elapsed time per iteration (s): 0.23 | learning rate: 2.219E-05 | global batch size: 256 | lm loss: 2.881485E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.184 | TFLOPs: 6.97 | +31: iteration 35250/ 37905 | consumed samples: 9024000 | consumed tokens: 18481152000 | elapsed time per iteration (s): 0.22 | learning rate: 2.217E-05 | global batch size: 256 | lm loss: 2.893328E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1150.302 | TFLOPs: 7.33 | +31: iteration 35260/ 37905 | consumed samples: 9026560 | consumed tokens: 18486394880 | elapsed time per iteration (s): 0.22 | learning rate: 2.215E-05 | global batch size: 256 | lm loss: 2.866169E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.515 | TFLOPs: 7.30 | +31: iteration 35270/ 37905 | consumed samples: 9029120 | consumed tokens: 18491637760 | elapsed time per iteration (s): 0.22 | learning rate: 2.214E-05 | global batch size: 256 | lm loss: 2.877990E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1154.402 | TFLOPs: 7.35 | +31: iteration 35280/ 37905 | consumed samples: 9031680 | consumed tokens: 18496880640 | elapsed time per iteration (s): 0.25 | learning rate: 2.212E-05 | global batch size: 256 | lm loss: 2.914790E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.691 | TFLOPs: 6.53 | +31: iteration 35290/ 37905 | consumed samples: 9034240 | consumed tokens: 18502123520 | elapsed time per iteration (s): 0.26 | learning rate: 2.211E-05 | global batch size: 256 | lm loss: 2.864683E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 985.414 | TFLOPs: 6.28 | +31: iteration 35300/ 37905 | consumed samples: 9036800 | consumed tokens: 18507366400 | elapsed time per iteration (s): 0.20 | learning rate: 2.209E-05 | global batch size: 256 | lm loss: 2.906040E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1293.793 | TFLOPs: 8.24 | +31: iteration 35310/ 37905 | consumed samples: 9039360 | consumed tokens: 18512609280 | elapsed time per iteration (s): 0.19 | learning rate: 2.207E-05 | global batch size: 256 | lm loss: 2.879732E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1335.889 | TFLOPs: 8.51 | +31: iteration 35320/ 37905 | consumed samples: 9041920 | consumed tokens: 18517852160 | elapsed time per iteration (s): 0.20 | learning rate: 2.206E-05 | global batch size: 256 | lm loss: 2.916145E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1283.086 | TFLOPs: 8.17 | +31: iteration 35330/ 37905 | consumed samples: 9044480 | consumed tokens: 18523095040 | elapsed time per iteration (s): 0.22 | learning rate: 2.204E-05 | global batch size: 256 | lm loss: 2.860791E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1163.262 | TFLOPs: 7.41 | +31: iteration 35340/ 37905 | consumed samples: 9047040 | consumed tokens: 18528337920 | elapsed time per iteration (s): 0.22 | learning rate: 2.203E-05 | global batch size: 256 | lm loss: 2.908966E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.914 | TFLOPs: 7.51 | +31: iteration 35350/ 37905 | consumed samples: 9049600 | consumed tokens: 18533580800 | elapsed time per iteration (s): 0.24 | learning rate: 2.201E-05 | global batch size: 256 | lm loss: 2.890601E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.078 | TFLOPs: 6.75 | +31: iteration 35360/ 37905 | consumed samples: 9052160 | consumed tokens: 18538823680 | elapsed time per iteration (s): 0.23 | learning rate: 2.199E-05 | global batch size: 256 | lm loss: 2.874931E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1091.425 | TFLOPs: 6.95 | +31: iteration 35370/ 37905 | consumed samples: 9054720 | consumed tokens: 18544066560 | elapsed time per iteration (s): 0.23 | learning rate: 2.198E-05 | global batch size: 256 | lm loss: 2.883595E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.532 | TFLOPs: 7.05 | +31: iteration 35380/ 37905 | consumed samples: 9057280 | consumed tokens: 18549309440 | elapsed time per iteration (s): 0.23 | learning rate: 2.196E-05 | global batch size: 256 | lm loss: 2.898235E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.915 | TFLOPs: 7.06 | +31: iteration 35390/ 37905 | consumed samples: 9059840 | consumed tokens: 18554552320 | elapsed time per iteration (s): 0.24 | learning rate: 2.195E-05 | global batch size: 256 | lm loss: 2.916144E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1066.060 | TFLOPs: 6.79 | +31: iteration 35400/ 37905 | consumed samples: 9062400 | consumed tokens: 18559795200 | elapsed time per iteration (s): 0.23 | learning rate: 2.193E-05 | global batch size: 256 | lm loss: 2.920786E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.140 | TFLOPs: 7.22 | +31: iteration 35410/ 37905 | consumed samples: 9064960 | consumed tokens: 18565038080 | elapsed time per iteration (s): 0.19 | learning rate: 2.192E-05 | global batch size: 256 | lm loss: 2.865910E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.942 | TFLOPs: 8.58 | +31: iteration 35420/ 37905 | consumed samples: 9067520 | consumed tokens: 18570280960 | elapsed time per iteration (s): 0.25 | learning rate: 2.190E-05 | global batch size: 256 | lm loss: 2.904895E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.337 | TFLOPs: 6.55 | +31: iteration 35430/ 37905 | consumed samples: 9070080 | consumed tokens: 18575523840 | elapsed time per iteration (s): 0.21 | learning rate: 2.189E-05 | global batch size: 256 | lm loss: 2.884515E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1205.101 | TFLOPs: 7.68 | +31: iteration 35440/ 37905 | consumed samples: 9072640 | consumed tokens: 18580766720 | elapsed time per iteration (s): 0.21 | learning rate: 2.187E-05 | global batch size: 256 | lm loss: 2.856167E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1243.347 | TFLOPs: 7.92 | +31: iteration 35450/ 37905 | consumed samples: 9075200 | consumed tokens: 18586009600 | elapsed time per iteration (s): 0.24 | learning rate: 2.186E-05 | global batch size: 256 | lm loss: 2.859883E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.031 | TFLOPs: 6.68 | +31: iteration 35460/ 37905 | consumed samples: 9077760 | consumed tokens: 18591252480 | elapsed time per iteration (s): 0.24 | learning rate: 2.184E-05 | global batch size: 256 | lm loss: 2.868030E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1052.894 | TFLOPs: 6.71 | +31: iteration 35470/ 37905 | consumed samples: 9080320 | consumed tokens: 18596495360 | elapsed time per iteration (s): 0.23 | learning rate: 2.183E-05 | global batch size: 256 | lm loss: 2.891086E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.007 | TFLOPs: 7.15 | +31: iteration 35480/ 37905 | consumed samples: 9082880 | consumed tokens: 18601738240 | elapsed time per iteration (s): 0.21 | learning rate: 2.181E-05 | global batch size: 256 | lm loss: 2.910039E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1204.557 | TFLOPs: 7.67 | +31: iteration 35490/ 37905 | consumed samples: 9085440 | consumed tokens: 18606981120 | elapsed time per iteration (s): 0.22 | learning rate: 2.180E-05 | global batch size: 256 | lm loss: 2.926867E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.880 | TFLOPs: 7.42 | +31: iteration 35500/ 37905 | consumed samples: 9088000 | consumed tokens: 18612224000 | elapsed time per iteration (s): 0.21 | learning rate: 2.178E-05 | global batch size: 256 | lm loss: 2.890158E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1197.964 | TFLOPs: 7.63 | +31: iteration 35510/ 37905 | consumed samples: 9090560 | consumed tokens: 18617466880 | elapsed time per iteration (s): 0.22 | learning rate: 2.177E-05 | global batch size: 256 | lm loss: 2.890013E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.355 | TFLOPs: 7.26 | +31: iteration 35520/ 37905 | consumed samples: 9093120 | consumed tokens: 18622709760 | elapsed time per iteration (s): 0.22 | learning rate: 2.175E-05 | global batch size: 256 | lm loss: 2.892388E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.651 | TFLOPs: 7.40 | +31: iteration 35530/ 37905 | consumed samples: 9095680 | consumed tokens: 18627952640 | elapsed time per iteration (s): 0.20 | learning rate: 2.174E-05 | global batch size: 256 | lm loss: 2.888327E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1271.374 | TFLOPs: 8.10 | +31: iteration 35540/ 37905 | consumed samples: 9098240 | consumed tokens: 18633195520 | elapsed time per iteration (s): 0.23 | learning rate: 2.172E-05 | global batch size: 256 | lm loss: 2.878195E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.065 | TFLOPs: 7.16 | +31: iteration 35550/ 37905 | consumed samples: 9100800 | consumed tokens: 18638438400 | elapsed time per iteration (s): 0.21 | learning rate: 2.171E-05 | global batch size: 256 | lm loss: 2.915497E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1247.312 | TFLOPs: 7.94 | +31: iteration 35560/ 37905 | consumed samples: 9103360 | consumed tokens: 18643681280 | elapsed time per iteration (s): 0.22 | learning rate: 2.169E-05 | global batch size: 256 | lm loss: 2.903506E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.038 | TFLOPs: 7.56 | +31: iteration 35570/ 37905 | consumed samples: 9105920 | consumed tokens: 18648924160 | elapsed time per iteration (s): 0.25 | learning rate: 2.168E-05 | global batch size: 256 | lm loss: 2.925285E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.952 | TFLOPs: 6.56 | +31: iteration 35580/ 37905 | consumed samples: 9108480 | consumed tokens: 18654167040 | elapsed time per iteration (s): 0.25 | learning rate: 2.167E-05 | global batch size: 256 | lm loss: 2.877026E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.193 | TFLOPs: 6.55 | +31: iteration 35590/ 37905 | consumed samples: 9111040 | consumed tokens: 18659409920 | elapsed time per iteration (s): 0.23 | learning rate: 2.165E-05 | global batch size: 256 | lm loss: 2.834660E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.126 | TFLOPs: 7.21 | +31: iteration 35600/ 37905 | consumed samples: 9113600 | consumed tokens: 18664652800 | elapsed time per iteration (s): 0.26 | learning rate: 2.164E-05 | global batch size: 256 | lm loss: 2.904895E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.996 | TFLOPs: 6.32 | +31: iteration 35610/ 37905 | consumed samples: 9116160 | consumed tokens: 18669895680 | elapsed time per iteration (s): 0.20 | learning rate: 2.162E-05 | global batch size: 256 | lm loss: 2.898576E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1260.255 | TFLOPs: 8.03 | +31: iteration 35620/ 37905 | consumed samples: 9118720 | consumed tokens: 18675138560 | elapsed time per iteration (s): 0.23 | learning rate: 2.161E-05 | global batch size: 256 | lm loss: 2.874897E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.607 | TFLOPs: 7.11 | +31: iteration 35630/ 37905 | consumed samples: 9121280 | consumed tokens: 18680381440 | elapsed time per iteration (s): 0.24 | learning rate: 2.160E-05 | global batch size: 256 | lm loss: 2.896286E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.349 | TFLOPs: 6.72 | +31: iteration 35640/ 37905 | consumed samples: 9123840 | consumed tokens: 18685624320 | elapsed time per iteration (s): 0.22 | learning rate: 2.158E-05 | global batch size: 256 | lm loss: 2.885142E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.706 | TFLOPs: 7.45 | +31: iteration 35650/ 37905 | consumed samples: 9126400 | consumed tokens: 18690867200 | elapsed time per iteration (s): 0.25 | learning rate: 2.157E-05 | global batch size: 256 | lm loss: 2.879933E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.694 | TFLOPs: 6.50 | +31: iteration 35660/ 37905 | consumed samples: 9128960 | consumed tokens: 18696110080 | elapsed time per iteration (s): 0.21 | learning rate: 2.155E-05 | global batch size: 256 | lm loss: 2.913168E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1212.471 | TFLOPs: 7.72 | +31: iteration 35670/ 37905 | consumed samples: 9131520 | consumed tokens: 18701352960 | elapsed time per iteration (s): 0.24 | learning rate: 2.154E-05 | global batch size: 256 | lm loss: 2.894180E+00 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1053.169 | TFLOPs: 6.71 | +31: iteration 35680/ 37905 | consumed samples: 9134080 | consumed tokens: 18706595840 | elapsed time per iteration (s): 0.21 | learning rate: 2.153E-05 | global batch size: 256 | lm loss: 2.905018E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1227.360 | TFLOPs: 7.82 | +31: iteration 35690/ 37905 | consumed samples: 9136640 | consumed tokens: 18711838720 | elapsed time per iteration (s): 0.21 | learning rate: 2.151E-05 | global batch size: 256 | lm loss: 2.856390E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1210.579 | TFLOPs: 7.71 | +31: iteration 35700/ 37905 | consumed samples: 9139200 | consumed tokens: 18717081600 | elapsed time per iteration (s): 0.21 | learning rate: 2.150E-05 | global batch size: 256 | lm loss: 2.877905E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1194.790 | TFLOPs: 7.61 | +31: iteration 35710/ 37905 | consumed samples: 9141760 | consumed tokens: 18722324480 | elapsed time per iteration (s): 0.21 | learning rate: 2.149E-05 | global batch size: 256 | lm loss: 2.911395E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1220.138 | TFLOPs: 7.77 | +31: iteration 35720/ 37905 | consumed samples: 9144320 | consumed tokens: 18727567360 | elapsed time per iteration (s): 0.22 | learning rate: 2.147E-05 | global batch size: 256 | lm loss: 2.850263E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1160.280 | TFLOPs: 7.39 | +31: iteration 35730/ 37905 | consumed samples: 9146880 | consumed tokens: 18732810240 | elapsed time per iteration (s): 0.21 | learning rate: 2.146E-05 | global batch size: 256 | lm loss: 2.919619E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1230.298 | TFLOPs: 7.84 | +31: iteration 35740/ 37905 | consumed samples: 9149440 | consumed tokens: 18738053120 | elapsed time per iteration (s): 0.26 | learning rate: 2.145E-05 | global batch size: 256 | lm loss: 2.902673E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 982.878 | TFLOPs: 6.26 | +31: iteration 35750/ 37905 | consumed samples: 9152000 | consumed tokens: 18743296000 | elapsed time per iteration (s): 0.23 | learning rate: 2.143E-05 | global batch size: 256 | lm loss: 2.903240E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1127.710 | TFLOPs: 7.18 | +31: iteration 35760/ 37905 | consumed samples: 9154560 | consumed tokens: 18748538880 | elapsed time per iteration (s): 0.21 | learning rate: 2.142E-05 | global batch size: 256 | lm loss: 2.872669E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1195.348 | TFLOPs: 7.61 | +31: iteration 35770/ 37905 | consumed samples: 9157120 | consumed tokens: 18753781760 | elapsed time per iteration (s): 0.20 | learning rate: 2.141E-05 | global batch size: 256 | lm loss: 2.877065E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.119 | TFLOPs: 8.22 | +31: iteration 35780/ 37905 | consumed samples: 9159680 | consumed tokens: 18759024640 | elapsed time per iteration (s): 0.23 | learning rate: 2.139E-05 | global batch size: 256 | lm loss: 2.879113E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1113.756 | TFLOPs: 7.09 | +31: iteration 35790/ 37905 | consumed samples: 9162240 | consumed tokens: 18764267520 | elapsed time per iteration (s): 0.26 | learning rate: 2.138E-05 | global batch size: 256 | lm loss: 2.869003E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 980.719 | TFLOPs: 6.25 | +31: iteration 35800/ 37905 | consumed samples: 9164800 | consumed tokens: 18769510400 | elapsed time per iteration (s): 0.28 | learning rate: 2.137E-05 | global batch size: 256 | lm loss: 2.894245E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 930.904 | TFLOPs: 5.93 | +31: iteration 35810/ 37905 | consumed samples: 9167360 | consumed tokens: 18774753280 | elapsed time per iteration (s): 0.22 | learning rate: 2.135E-05 | global batch size: 256 | lm loss: 2.899585E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1140.150 | TFLOPs: 7.26 | +31: iteration 35820/ 37905 | consumed samples: 9169920 | consumed tokens: 18779996160 | elapsed time per iteration (s): 0.29 | learning rate: 2.134E-05 | global batch size: 256 | lm loss: 2.879505E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 878.401 | TFLOPs: 5.59 | +31: iteration 35830/ 37905 | consumed samples: 9172480 | consumed tokens: 18785239040 | elapsed time per iteration (s): 0.23 | learning rate: 2.133E-05 | global batch size: 256 | lm loss: 2.854291E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1135.610 | TFLOPs: 7.23 | +31: iteration 35840/ 37905 | consumed samples: 9175040 | consumed tokens: 18790481920 | elapsed time per iteration (s): 0.21 | learning rate: 2.132E-05 | global batch size: 256 | lm loss: 2.861192E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1200.189 | TFLOPs: 7.64 | +31: iteration 35850/ 37905 | consumed samples: 9177600 | consumed tokens: 18795724800 | elapsed time per iteration (s): 0.23 | learning rate: 2.130E-05 | global batch size: 256 | lm loss: 2.906932E+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: 7.18 | +31: iteration 35860/ 37905 | consumed samples: 9180160 | consumed tokens: 18800967680 | elapsed time per iteration (s): 0.23 | learning rate: 2.129E-05 | global batch size: 256 | lm loss: 2.886453E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1134.979 | TFLOPs: 7.23 | +31: iteration 35870/ 37905 | consumed samples: 9182720 | consumed tokens: 18806210560 | elapsed time per iteration (s): 0.23 | learning rate: 2.128E-05 | global batch size: 256 | lm loss: 2.935068E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1137.506 | TFLOPs: 7.24 | +31: iteration 35880/ 37905 | consumed samples: 9185280 | consumed tokens: 18811453440 | elapsed time per iteration (s): 0.22 | learning rate: 2.126E-05 | global batch size: 256 | lm loss: 2.882991E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1141.101 | TFLOPs: 7.27 | +31: iteration 35890/ 37905 | consumed samples: 9187840 | consumed tokens: 18816696320 | elapsed time per iteration (s): 0.21 | learning rate: 2.125E-05 | global batch size: 256 | lm loss: 2.881441E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1201.708 | TFLOPs: 7.65 | +31: iteration 35900/ 37905 | consumed samples: 9190400 | consumed tokens: 18821939200 | elapsed time per iteration (s): 0.22 | learning rate: 2.124E-05 | global batch size: 256 | lm loss: 2.896931E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1175.302 | TFLOPs: 7.49 | +31: iteration 35910/ 37905 | consumed samples: 9192960 | consumed tokens: 18827182080 | elapsed time per iteration (s): 0.21 | learning rate: 2.123E-05 | global batch size: 256 | lm loss: 2.881401E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1228.862 | TFLOPs: 7.83 | +31: iteration 35920/ 37905 | consumed samples: 9195520 | consumed tokens: 18832424960 | elapsed time per iteration (s): 0.25 | learning rate: 2.122E-05 | global batch size: 256 | lm loss: 2.904857E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1014.960 | TFLOPs: 6.46 | +31: iteration 35930/ 37905 | consumed samples: 9198080 | consumed tokens: 18837667840 | elapsed time per iteration (s): 0.24 | learning rate: 2.120E-05 | global batch size: 256 | lm loss: 2.866739E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1057.298 | TFLOPs: 6.73 | +31: iteration 35940/ 37905 | consumed samples: 9200640 | consumed tokens: 18842910720 | elapsed time per iteration (s): 0.22 | learning rate: 2.119E-05 | global batch size: 256 | lm loss: 2.878700E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.083 | TFLOPs: 7.53 | +31: iteration 35950/ 37905 | consumed samples: 9203200 | consumed tokens: 18848153600 | elapsed time per iteration (s): 0.53 | learning rate: 2.118E-05 | global batch size: 256 | lm loss: 2.906329E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 486.338 | TFLOPs: 3.10 | +31: iteration 35960/ 37905 | consumed samples: 9205760 | consumed tokens: 18853396480 | elapsed time per iteration (s): 0.22 | learning rate: 2.117E-05 | global batch size: 256 | lm loss: 2.919844E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.679 | TFLOPs: 7.30 | +31: iteration 35970/ 37905 | consumed samples: 9208320 | consumed tokens: 18858639360 | elapsed time per iteration (s): 0.26 | learning rate: 2.116E-05 | global batch size: 256 | lm loss: 2.895529E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 990.711 | TFLOPs: 6.31 | +31: iteration 35980/ 37905 | consumed samples: 9210880 | consumed tokens: 18863882240 | elapsed time per iteration (s): 0.24 | learning rate: 2.114E-05 | global batch size: 256 | lm loss: 2.869380E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.416 | TFLOPs: 6.86 | +31: iteration 35990/ 37905 | consumed samples: 9213440 | consumed tokens: 18869125120 | elapsed time per iteration (s): 0.22 | learning rate: 2.113E-05 | global batch size: 256 | lm loss: 2.874342E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.643 | TFLOPs: 7.26 | + 0: [2022-11-24 16:22:49,466] [INFO] [logging.py:68:log_dist] [Rank 0] step=36000, skipped=0, lr=[2.1119546880181567e-05, 2.1119546880181567e-05, 2.1119546880181567e-05], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +31: iteration 36000/ 37905 | consumed samples: 9216000 | consumed tokens: 18874368000 | elapsed time per iteration (s): 0.20 | learning rate: 2.112E-05 | global batch size: 256 | lm loss: 2.902389E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1274.282 | TFLOPs: 8.12 | + 0: steps: 36000 loss: 2.9303 iter time (s): 0.225 samples/sec: 1139.668 +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 36000 | lm loss value: 2.809536E+00 | lm loss PPL: 1.660221E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 36000 to checkpoints_83m + 0: [2022-11-24 16:22:49,565] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step36000 is begin to save! + 0: [2022-11-24 16:22:49,601] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,697] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,718] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,742] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,742] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,754] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,765] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,765] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,777] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,777] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,801] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,812] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,812] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:22:49,825] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:22:49,825] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step36000/mp_rank_00_model_states.pt + 0: [2022-11-24 16:22:49,825] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:22:49,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:22:49,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step36000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:22:49,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:49,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:22:49,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:49,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:49,917] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:22:49,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 4: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 5: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +23: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +31: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:49,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:49,918] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:49,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:22:49,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:22:49,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:49,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,919] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:49,919] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:49,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:49,925] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:49,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:22:49,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:49,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:49,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +17: [2022-11-24 16:22:49,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:49,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +29: [2022-11-24 16:22:49,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:49,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:49,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:49,926] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:49,926] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:49,926] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,927] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:49,927] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +20: [2022-11-24 16:22:49,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:22:49,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:49,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:49,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:49,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:49,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +13: [2022-11-24 16:22:49,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:49,936] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 1: [2022-11-24 16:22:49,936] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:22:49,936] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:49,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:49,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:22:49,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:49,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:49,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:49,937] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:49,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:49,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:49,937] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:49,937] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:49,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:49,945] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:22:49,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:49,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +23: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:22:49,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:49,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:49,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +31: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:49,946] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:49,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:49,946] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 9: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:49,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 9: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:22:49,947] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:49,947] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:49,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:49,948] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +27: [2022-11-24 16:22:49,948] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 4: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:49,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:22:49,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +24: [2022-11-24 16:22:49,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +26: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:22:49,950] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:49,950] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +14: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:49,951] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:49,951] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,951] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:49,951] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:49,951] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:22:49,951] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +20: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:22:49,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:49,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:49,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 2: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:49,952] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +29: [2022-11-24 16:22:49,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:49,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:49,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:49,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:49,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +10: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:49,953] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:49,953] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:49,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:22:49,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 1: [2022-11-24 16:22:49,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:22:49,954] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:49,954] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +23: [2022-11-24 16:22:49,957] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:22:49,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:49,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:49,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:49,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:49,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 5: [2022-11-24 16:22:49,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:49,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:49,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:49,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:22:49,958] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:49,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 9: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt +31: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:49,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:49,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +24: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:22:49,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:49,959] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:49,959] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:22:49,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:49,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:49,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:49,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,960] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,960] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:22:49,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:49,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:49,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:49,961] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +29: [2022-11-24 16:22:49,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:49,962] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:49,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 2: [2022-11-24 16:22:49,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:49,962] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:22:49,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:49,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:22:49,962] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:49,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:49,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:49,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +10: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:49,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 1: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:49,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:49,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:49,963] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:22:49,963] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:49,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:22:49,964] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:49,964] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 9: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +23: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:22:49,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 5: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:49,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:49,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:49,966] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:49,966] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:49,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:22:49,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:49,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:49,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:49,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 16:22:49,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:49,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:22:49,967] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:49,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 4: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:49,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:49,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +24: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:22:49,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:49,968] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +17: [2022-11-24 16:22:49,968] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:22:49,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +14: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:49,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:22:49,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +20: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:22:49,969] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,969] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:49,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +29: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:49,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:49,970] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:49,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 2: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:49,971] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 1: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:22:49,971] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:49,971] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:49,971] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 16:22:49,971] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +10: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:49,972] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:49,972] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:49,972] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:49,972] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:22:49,972] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 9: [2022-11-24 16:22:49,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:49,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:22:49,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:49,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:49,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +23: [2022-11-24 16:22:49,973] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:49,973] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:49,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:22:49,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:49,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:49,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:49,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:49,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:49,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 5: [2022-11-24 16:22:49,974] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:49,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:49,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:49,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:49,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:49,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:49,975] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:49,975] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:49,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:22:49,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:49,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 4: [2022-11-24 16:22:49,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:49,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:49,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:49,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:22:49,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +24: [2022-11-24 16:22:49,976] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:49,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +24: [2022-11-24 16:22:49,976] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:49,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:49,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:49,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +14: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:49,977] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:49,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:49,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +20: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:22:49,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:49,978] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:49,978] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:49,979] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:49,979] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:49,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:22:49,979] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:49,979] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 2: [2022-11-24 16:22:49,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:49,979] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:22:49,979] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:49,979] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +10: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 1: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +13: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +23: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:22:49,980] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:49,980] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:22:49,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:49,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 9: [2022-11-24 16:22:49,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:49,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:22:49,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +31: [2022-11-24 16:22:49,981] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:49,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 5: [2022-11-24 16:22:49,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:49,981] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:49,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:49,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:49,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:49,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:22:49,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:49,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +24: [2022-11-24 16:22:49,982] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:49,982] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 16:22:49,982] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 4: [2022-11-24 16:22:49,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:49,993] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:49,993] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:22:49,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +17: [2022-11-24 16:22:49,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:22:49,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +14: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:49,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:49,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:49,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:22:49,994] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +20: [2022-11-24 16:22:49,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:49,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 2: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:49,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:22:49,995] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:49,995] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +29: [2022-11-24 16:22:49,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:49,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:49,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:49,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:22:49,996] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:49,996] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 1: [2022-11-24 16:22:50,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:22:50,001] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:50,001] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:50,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:50,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +27: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:50,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:50,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:50,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +23: [2022-11-24 16:22:50,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:22:50,002] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 9: [2022-11-24 16:22:50,002] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:50,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:50,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:50,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 5: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:50,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:50,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:50,003] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:22:50,003] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 4: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:50,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:22:50,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +24: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:50,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:50,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:50,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:50,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:22:50,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:50,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +17: [2022-11-24 16:22:50,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +14: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: [2022-11-24 16:22:50,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:22:50,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:50,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +20: [2022-11-24 16:22:50,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:22:50,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:22:50,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:50,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:50,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +29: [2022-11-24 16:22:50,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:50,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:22:50,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 16:22:50,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 2: [2022-11-24 16:22:50,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:50,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:50,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:50,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:22:50,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:50,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:50,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:22:50,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:50,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +27: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +21: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +10: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 1: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 8: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt + 5: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 7: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +23: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +31: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +30: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt +18: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +30: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 7: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +18: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt + 9: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt + 4: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +24: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +12: [2022-11-24 16:22:50,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:22:50,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +29: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +25: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +14: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +29: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +22: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +20: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +22: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +20: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +25: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 0: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +14: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +26: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +21: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +28: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +26: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +11: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +27: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +11: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +27: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +17: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +15: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +10: [2022-11-24 16:22:50,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +15: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +10: [2022-11-24 16:22:50,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +16: [2022-11-24 16:22:50,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:22:50,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 16:22:50,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:50,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:50,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:50,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 6: [2022-11-24 16:22:50,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:50,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:22:50,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 16:22:50,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:50,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +13: [2022-11-24 16:22:50,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 2: [2022-11-24 16:22:50,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:22:50,019] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 2: [2022-11-24 16:22:50,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:50,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:50,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:50,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +13: [2022-11-24 16:22:50,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:22:50,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 16:22:50,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! +19: [2022-11-24 16:22:50,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:22:50,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 16:22:50,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 3: [2022-11-24 16:22:50,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step36000 is ready now! + 0: successfully saved checkpoint at iteration 36000 to checkpoints_83m +31: time (ms) | save-checkpoint: 497.16 +31: iteration 36010/ 37905 | consumed samples: 9218560 | consumed tokens: 18879610880 | elapsed time per iteration (s): 0.30 | learning rate: 2.111E-05 | global batch size: 256 | lm loss: 2.875034E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 854.731 | TFLOPs: 5.44 | +31: iteration 36020/ 37905 | consumed samples: 9221120 | consumed tokens: 18884853760 | elapsed time per iteration (s): 0.24 | learning rate: 2.110E-05 | global batch size: 256 | lm loss: 2.886648E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1046.760 | TFLOPs: 6.67 | +31: iteration 36030/ 37905 | consumed samples: 9223680 | consumed tokens: 18890096640 | elapsed time per iteration (s): 0.26 | learning rate: 2.108E-05 | global batch size: 256 | lm loss: 2.865829E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1002.599 | TFLOPs: 6.39 | +31: iteration 36040/ 37905 | consumed samples: 9226240 | consumed tokens: 18895339520 | elapsed time per iteration (s): 0.25 | learning rate: 2.107E-05 | global batch size: 256 | lm loss: 2.881052E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1014.956 | TFLOPs: 6.46 | +31: iteration 36050/ 37905 | consumed samples: 9228800 | consumed tokens: 18900582400 | elapsed time per iteration (s): 0.33 | learning rate: 2.106E-05 | global batch size: 256 | lm loss: 2.905450E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 777.405 | TFLOPs: 4.95 | +31: iteration 36060/ 37905 | consumed samples: 9231360 | consumed tokens: 18905825280 | elapsed time per iteration (s): 0.27 | learning rate: 2.105E-05 | global batch size: 256 | lm loss: 2.913760E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 935.827 | TFLOPs: 5.96 | +31: iteration 36070/ 37905 | consumed samples: 9233920 | consumed tokens: 18911068160 | elapsed time per iteration (s): 0.26 | learning rate: 2.104E-05 | global batch size: 256 | lm loss: 2.899444E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.116 | TFLOPs: 6.37 | +31: iteration 36080/ 37905 | consumed samples: 9236480 | consumed tokens: 18916311040 | elapsed time per iteration (s): 0.23 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.876626E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1107.643 | TFLOPs: 7.05 | +31: iteration 36090/ 37905 | consumed samples: 9239040 | consumed tokens: 18921553920 | elapsed time per iteration (s): 0.24 | learning rate: 2.102E-05 | global batch size: 256 | lm loss: 2.869850E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1076.226 | TFLOPs: 6.85 | +31: iteration 36100/ 37905 | consumed samples: 9241600 | consumed tokens: 18926796800 | elapsed time per iteration (s): 0.24 | learning rate: 2.101E-05 | global batch size: 256 | lm loss: 2.925788E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1071.731 | TFLOPs: 6.83 | +31: iteration 36110/ 37905 | consumed samples: 9244160 | consumed tokens: 18932039680 | elapsed time per iteration (s): 0.25 | learning rate: 2.099E-05 | global batch size: 256 | lm loss: 2.901951E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1019.844 | TFLOPs: 6.50 | +31: iteration 36120/ 37905 | consumed samples: 9246720 | consumed tokens: 18937282560 | elapsed time per iteration (s): 0.20 | learning rate: 2.098E-05 | global batch size: 256 | lm loss: 2.886228E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1281.352 | TFLOPs: 8.16 | +31: iteration 36130/ 37905 | consumed samples: 9249280 | consumed tokens: 18942525440 | elapsed time per iteration (s): 0.23 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 2.864394E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1101.560 | TFLOPs: 7.02 | +31: iteration 36140/ 37905 | consumed samples: 9251840 | consumed tokens: 18947768320 | elapsed time per iteration (s): 0.35 | learning rate: 2.096E-05 | global batch size: 256 | lm loss: 2.870307E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 725.824 | TFLOPs: 4.62 | +31: iteration 36150/ 37905 | consumed samples: 9254400 | consumed tokens: 18953011200 | elapsed time per iteration (s): 0.22 | learning rate: 2.095E-05 | global batch size: 256 | lm loss: 2.926268E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1164.147 | TFLOPs: 7.41 | +31: iteration 36160/ 37905 | consumed samples: 9256960 | consumed tokens: 18958254080 | elapsed time per iteration (s): 0.28 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 2.925979E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 912.410 | TFLOPs: 5.81 | +31: iteration 36170/ 37905 | consumed samples: 9259520 | consumed tokens: 18963496960 | elapsed time per iteration (s): 0.24 | learning rate: 2.093E-05 | global batch size: 256 | lm loss: 2.908002E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1077.114 | TFLOPs: 6.86 | +31: iteration 36180/ 37905 | consumed samples: 9262080 | consumed tokens: 18968739840 | elapsed time per iteration (s): 0.24 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.891486E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1062.556 | TFLOPs: 6.77 | +31: iteration 36190/ 37905 | consumed samples: 9264640 | consumed tokens: 18973982720 | elapsed time per iteration (s): 0.24 | learning rate: 2.091E-05 | global batch size: 256 | lm loss: 2.885267E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1056.086 | TFLOPs: 6.73 | +31: iteration 36200/ 37905 | consumed samples: 9267200 | consumed tokens: 18979225600 | elapsed time per iteration (s): 0.22 | learning rate: 2.090E-05 | global batch size: 256 | lm loss: 2.914770E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1185.537 | TFLOPs: 7.55 | +31: iteration 36210/ 37905 | consumed samples: 9269760 | consumed tokens: 18984468480 | elapsed time per iteration (s): 0.21 | learning rate: 2.089E-05 | global batch size: 256 | lm loss: 2.879210E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1239.101 | TFLOPs: 7.89 | +31: iteration 36220/ 37905 | consumed samples: 9272320 | consumed tokens: 18989711360 | elapsed time per iteration (s): 0.24 | learning rate: 2.088E-05 | global batch size: 256 | lm loss: 2.916792E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.863 | TFLOPs: 6.90 | +31: iteration 36230/ 37905 | consumed samples: 9274880 | consumed tokens: 18994954240 | elapsed time per iteration (s): 0.25 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 2.907865E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.403 | TFLOPs: 6.62 | +31: iteration 36240/ 37905 | consumed samples: 9277440 | consumed tokens: 19000197120 | elapsed time per iteration (s): 0.22 | learning rate: 2.086E-05 | global batch size: 256 | lm loss: 2.906250E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1187.042 | TFLOPs: 7.56 | +31: iteration 36250/ 37905 | consumed samples: 9280000 | consumed tokens: 19005440000 | elapsed time per iteration (s): 0.44 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 2.873895E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 587.986 | TFLOPs: 3.74 | +31: iteration 36260/ 37905 | consumed samples: 9282560 | consumed tokens: 19010682880 | elapsed time per iteration (s): 0.22 | learning rate: 2.084E-05 | global batch size: 256 | lm loss: 2.863333E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.169 | TFLOPs: 7.30 | +31: iteration 36270/ 37905 | consumed samples: 9285120 | consumed tokens: 19015925760 | elapsed time per iteration (s): 0.23 | learning rate: 2.083E-05 | global batch size: 256 | lm loss: 2.908844E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.491 | TFLOPs: 7.20 | +31: iteration 36280/ 37905 | consumed samples: 9287680 | consumed tokens: 19021168640 | elapsed time per iteration (s): 0.25 | learning rate: 2.082E-05 | global batch size: 256 | lm loss: 2.878504E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1005.100 | TFLOPs: 6.40 | +31: iteration 36290/ 37905 | consumed samples: 9290240 | consumed tokens: 19026411520 | elapsed time per iteration (s): 0.28 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.909422E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 927.002 | TFLOPs: 5.90 | +31: iteration 36300/ 37905 | consumed samples: 9292800 | consumed tokens: 19031654400 | elapsed time per iteration (s): 0.24 | learning rate: 2.080E-05 | global batch size: 256 | lm loss: 2.912795E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1047.331 | TFLOPs: 6.67 | diff --git a/logs/2058110_119.err b/logs/2058110_119.err new file mode 100644 index 0000000000000000000000000000000000000000..5103606b5ebb94c4aafd3d77fcbad36b3e319c2d --- /dev/null +++ b/logs/2058110_119.err @@ -0,0 +1,1983 @@ +21: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +21: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +21: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +19: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': 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 +23: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +23: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +23: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +20: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +20: rm: cannot remove '/dev/shm/hsakmt_shared_mem': 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. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 8: Successfully preprocessed all matching files. + 8: Successfully preprocessed all matching files. + 8: Successfully preprocessed all matching files. +10: Successfully preprocessed all matching files. +10: Successfully preprocessed all matching files. +10: Successfully preprocessed all matching files. +26: Successfully preprocessed all matching files. +26: Successfully preprocessed all matching files. +11: Successfully preprocessed all matching files. +14: Successfully preprocessed all matching files. +19: Successfully preprocessed all matching files. +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( +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( + 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( + 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( +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( +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( + 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( + 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( + 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( +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( +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( + 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( + 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( + 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( +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( + 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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( + 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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( + 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( +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( +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( + 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( +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( + 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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( + 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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( + 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... + 7: 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... +18: 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... +24: 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... + 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... + 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... + 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: + 1: + 1: + 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: + 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... + 3: + 3: + 3: + 3: + 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: + 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... + 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... + 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... + 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... + 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... + 5: + 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...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: + 5: + 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...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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: + 7: 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... +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... +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... +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... +10: 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: +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: +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... +11: +11: + 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: + 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: Using /pfs/lustrep4/users/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: +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... +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... +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... +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... +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... +15: +15: 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...Using /pfs/lustrep4/users/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: +12: +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... +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: Using /pfs/lustrep4/users/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: +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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: +13: +13: +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: 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: 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... +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... +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... +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...Using /pfs/lustrep4/users/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: +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... +19: +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: Using /pfs/lustrep4/users/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: Using /pfs/lustrep4/users/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: +17: +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: +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... +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... +23: 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +20: +24: 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... +24: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: +21: +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... +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... +24: 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...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: +22: +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: +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... +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... +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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: +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... +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... +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...Using /pfs/lustrep4/users/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... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: +28: +28: +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...Using /pfs/lustrep4/users/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: +27: +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... +29: +29: +29: +29: +29: 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: +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: Using /pfs/lustrep4/users/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: +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...Using /pfs/lustrep4/users/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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/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: + 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... + 3: Loading extension module utils... + 7: Loading extension module utils... + 3: Loading extension module utils... + 7: Loading extension module utils... + 7: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... + 7: Loading extension module utils... + 3: Loading extension module utils... + 7: Loading extension module utils... + 3: Loading extension module utils... + 7: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... + 7: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 5: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 5: Loading extension module utils... + 5: Loading extension module utils... + 8: Loading extension module utils... + 6: Loading extension module utils... + 5: Loading extension module utils... + 8: Loading extension module utils... + 5: Loading extension module utils... + 6: Loading extension module utils... + 8: 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... + 6: Loading extension module utils... +10: Loading extension module utils... + 6: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... +11: Loading extension module utils... + 9: Loading extension module utils... +11: Loading extension module utils... + 9: Loading extension module utils... +11: 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... + 9: Loading extension module utils... + 9: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +15: Loading extension module utils... +14: Loading extension module utils... +15: Loading extension module utils... +14: Loading extension module utils... +15: Loading extension module utils... +14: 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... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +18: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +18: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +18: Loading extension module utils... +13: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +18: Loading extension module utils... +13: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +19: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +19: Loading extension module utils... +16: Loading extension module utils... +19: Loading extension module utils... +16: Loading extension module utils... +19: Loading extension module utils... +19: Loading extension module utils... +16: Loading extension module utils... +19: Loading extension module utils... +19: Loading extension module utils... +19: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +23: Loading extension module utils... +23: Loading extension module utils... +23: Loading extension module utils... +24: 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... +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... +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... +20: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +21: Loading extension module utils... +20: Loading extension module utils... +21: Loading extension module utils... +21: 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... +22: Loading extension module utils... +22: Loading extension module utils... +22: Loading extension module utils... +22: Loading extension module utils... +22: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: 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... + 0: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +28: Loading extension module utils... +27: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +27: Loading extension module utils... +28: Loading extension module utils... +27: Loading extension module utils... +28: Loading extension module utils... +27: Loading extension module utils... +28: Loading extension module utils... +27: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +29: 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... +29: 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... +29: 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... + 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... + 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... + 2: Loading extension module utils... + 2: Loading extension module utils... + 2: 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... + 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: 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: 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 3: + 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... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +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... +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... +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... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: 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: + 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... + 6: + 6: + 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... + 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...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... + 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: 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: 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... + 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... +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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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: +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: 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... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +18: +18: Loading extension module utils... + 5: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: 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: + 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... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +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... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... +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... + 5: No modifications detected for re-loaded extension module utils, skipping build step... + 5: Loading extension module utils... +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... + 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... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: 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: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 5: + 5: Loading extension module utils... +30: 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... +30: +30: +30: +30: Loading extension module utils...Loading extension module utils... +30: Loading extension module utils...Loading extension module utils... +30: +30: +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: 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... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: 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... +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... +19: +19: +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... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: +14: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: 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... +19: +19: Loading extension module utils... +19: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +19: +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... +14: +14: +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +19: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +19: +19: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +19: +19: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Loading extension module utils... +14: +19: No modifications detected for re-loaded extension module utils, skipping build step... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +19: Loading extension module utils... +14: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +14: +14: Loading extension module utils...Loading extension module utils... +14: +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: 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... + 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... + 2: + 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... +20: 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... +20: 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... +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: No modifications detected for re-loaded extension module utils, skipping build step... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: Loading extension module utils... +20: 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... +20: +20: 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... +20: 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... +20: No modifications detected for re-loaded extension module utils, skipping build step... +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... +20: Loading extension module utils... +31: 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... +31: 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...No modifications detected for re-loaded extension module utils, skipping build step... +20: +20: 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... +28: 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... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: 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: + 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... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +15: +28: 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... + 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... +28: 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: +15: +29: 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... +15: 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... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 2: No modifications detected for re-loaded extension module utils, skipping build step... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 2: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: No modifications detected for re-loaded extension module utils, skipping build step... +29: 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... +31: Loading extension module utils... +17: 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... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: 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...Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +28: +29: +29: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Loading extension module utils...Loading extension module utils... +28: +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +29: +29: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...Loading extension module utils... +29: +29: +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +17: Loading extension module utils... +28: 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... +15: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +29: 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... +17: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +15: Loading extension module utils... +17: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: 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... +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... +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... +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... +10: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +10: 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... +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: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +10: +10: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +10: +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: +10: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +10: +10: Loading extension module utils... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +13: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: Loading extension module utils... +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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +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... +13: Loading extension module utils... +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... +13: Loading extension module utils... +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... +13: Loading extension module utils... +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... +13: 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... +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... +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: 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... +26: Loading extension module utils... +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... +26: Loading extension module utils... +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... +26: Loading extension module utils... +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... +26: 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... +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... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: 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... +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: +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... +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... +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... + 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... + 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... + 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... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +11: +11: Loading extension module utils... +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... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +27: 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... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +27: 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: 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... +11: +11: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +11: +11: Loading extension module utils... +27: 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... +12: 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... +12: 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... +16: 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... +12: 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...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: +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: 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: + 1: 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... +16: +16: 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...No modifications detected for re-loaded extension module utils, skipping build step... + 8: + 8: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +22: 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... +27: 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... +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: + 8: + 8: + 8: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 8: +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: 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... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 8: Loading extension module utils... + 8: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: 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... + 8: Loading extension module utils... +22: 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... +27: Loading extension module utils... + 1: 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: 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...No modifications detected for re-loaded extension module utils, skipping build step... + 7: + 7: Loading extension module utils...Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 7: + 7: + 1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 7: 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... +23: 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... + 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: + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +23: +23: Loading extension module utils... +27: 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... + 7: Loading extension module utils...Loading extension module utils... + 7: +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...No modifications detected for re-loaded extension module utils, skipping build step... +27: +27: +27: Loading extension module utils...Loading extension module utils...Loading extension module utils... +27: +27: + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... + 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... + 9: + 9: +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +23: +23: 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... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... + 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: +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... + 9: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: 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... +27: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +23: +23: Loading extension module utils...Loading extension module utils... +23: +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +27: 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... +27: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +22: 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...Loading extension module utils... +22: +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: 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... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +22: 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... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: 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: +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +16: 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... + 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: +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... + 1: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils... +16: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: 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... +16: +16: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +12: Loading extension module utils... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: Loading extension module utils... + 1: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... + 9: + 9: Loading extension module utils... + 9: No modifications detected for re-loaded extension module utils, skipping build step... + 9: 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...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: + 4: + 4: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... + 4: + 4: + 4: + 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... + 4: No modifications detected for re-loaded extension module utils, skipping build step... + 4: 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... +21: 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: 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: 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: Using /pfs/lustrep4/users/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: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +21: +21: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +21: +21: +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +25: 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... +25: 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: 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... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +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... +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... + 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") + 1: Inconsistency detected by ld.so: dl-open.c: 881: _dl_open: Assertion `_dl_debug_initialize (0, args.nsid)->r_state == RT_CONSISTENT' failed! + 5: Inconsistency detected by ld.so: dl-open.c: 881: _dl_open: Assertion `_dl_debug_initialize (0, args.nsid)->r_state == RT_CONSISTENT' failed! + 1: Traceback (most recent call last): + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1120, in _try_get_data + 1: data = self._data_queue.get(timeout=timeout) + 1: File "/opt/cray/pe/python/3.9.12.1/lib/python3.9/queue.py", line 179, in get + 1: raise Empty + 1: _queue.Empty + 1: + 1: The above exception was the direct cause of the following exception: + 1: + 1: Traceback (most recent call last): + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/pretrain_gpt.py", line 235, in + 1: main() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346, in wrapper + 1: return f(*args, **kwargs) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/pretrain_gpt.py", line 231, in main + 1: pretrain(train_valid_test_datasets_provider, model_provider, forward_step, + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 188, in pretrain + 1: iteration = train(forward_step_func, + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 976, in train + 1: evaluate_and_print_results(prefix, forward_step_func, + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 1102, in evaluate_and_print_results + 1: total_loss_dict = evaluate(forward_step_func, data_iterator, model, verbose) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 1055, in evaluate + 1: loss = model[0].eval_batch(data_iterator) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 443, in eval_batch + 1: self._exec_schedule(sched) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 1377, in _exec_schedule + 1: self._exec_instr(**cmd.kwargs) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 791, in _exec_load_micro_batch + 1: batch = self._next_batch() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 623, in _next_batch + 1: batch = next(self.data_iterator) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 628, in __next__ + 1: data = self._next_data() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1316, in _next_data + 1: idx, data = self._get_data() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1272, in _get_data + 1: success, data = self._try_get_data() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1133, in _try_get_data + 1: raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) from e + 1: RuntimeError: DataLoader worker (pid(s) 15957) exited unexpectedly + 1: WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 12864 closing signal SIGTERM + 1: WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 12865 closing signal SIGTERM + 1: WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 12867 closing signal SIGTERM + 1: WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 12868 closing signal SIGTERM + 1: WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 12869 closing signal SIGTERM + 1: WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 12870 closing signal SIGTERM + 1: WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 12871 closing signal SIGTERM + 1: ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 2 (pid: 12866) of binary: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/bin/python + 1: ERROR:torch.distributed.elastic.agent.server.api:Error waiting on exit barrier. Elapsed: 307.0006730556488 seconds + 1: Traceback (most recent call last): + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/elastic/agent/server/api.py", line 906, in _exit_barrier + 1: store_util.barrier( + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/elastic/utils/store.py", line 78, in barrier + 1: synchronize(store, data, rank, world_size, key_prefix, barrier_timeout) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/elastic/utils/store.py", line 64, in synchronize + 1: agent_data = get_all(store, rank, key_prefix, world_size) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/elastic/utils/store.py", line 34, in get_all + 1: data = store.get(f"{prefix}{idx}") + 1: RuntimeError: Socket Timeout + 1: ERROR:torch.distributed.elastic.multiprocessing.errors.error_handler:no error file defined for parent, to copy child error file (/tmp/torchelastic_o8_0_qrm/none_n8t6rxem/attempt_0/2/error.json) + 1: Traceback (most recent call last): + 1: File "/opt/cray/pe/python/3.9.12.1/lib/python3.9/runpy.py", line 197, in _run_module_as_main + 1: return _run_code(code, main_globals, None, + 1: File "/opt/cray/pe/python/3.9.12.1/lib/python3.9/runpy.py", line 87, in _run_code + 1: exec(code, run_globals) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/run.py", line 766, in + 1: main() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346, in wrapper + 1: return f(*args, **kwargs) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/run.py", line 762, in main + 1: run(args) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/run.py", line 753, in run + 1: elastic_launch( + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/launcher/api.py", line 132, in __call__ + 1: return launch_agent(self._config, self._entrypoint, list(args)) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/launcher/api.py", line 246, in launch_agent + 1: raise ChildFailedError( + 1: torch.distributed.elastic.multiprocessing.errors.ChildFailedError: + 1: ============================================================ + 1: Megatron-DeepSpeed/pretrain_gpt.py FAILED + 1: ------------------------------------------------------------ + 1: Failures: + 1: + 1: ------------------------------------------------------------ + 1: Root Cause (first observed failure): + 1: [0]: + 1: time : 2022-11-24_16:53:38 + 1: host : nid005361 + 1: rank : 10 (local_rank: 2) + 1: exitcode : 1 (pid: 12866) + 1: error_file: /tmp/torchelastic_o8_0_qrm/none_n8t6rxem/attempt_0/2/error.json + 1: traceback : Traceback (most recent call last): + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1120, in _try_get_data + 1: data = self._data_queue.get(timeout=timeout) + 1: File "/opt/cray/pe/python/3.9.12.1/lib/python3.9/queue.py", line 179, in get + 1: raise Empty + 1: _queue.Empty + 1: + 1: The above exception was the direct cause of the following exception: + 1: + 1: Traceback (most recent call last): + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346, in wrapper + 1: return f(*args, **kwargs) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/pretrain_gpt.py", line 231, in main + 1: pretrain(train_valid_test_datasets_provider, model_provider, forward_step, + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 188, in pretrain + 1: iteration = train(forward_step_func, + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 976, in train + 1: evaluate_and_print_results(prefix, forward_step_func, + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 1102, in evaluate_and_print_results + 1: total_loss_dict = evaluate(forward_step_func, data_iterator, model, verbose) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/training.py", line 1055, in evaluate + 1: loss = model[0].eval_batch(data_iterator) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 443, in eval_batch + 1: self._exec_schedule(sched) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 1377, in _exec_schedule + 1: self._exec_instr(**cmd.kwargs) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 791, in _exec_load_micro_batch + 1: batch = self._next_batch() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed/runtime/pipe/engine.py", line 623, in _next_batch + 1: batch = next(self.data_iterator) + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 628, in __next__ + 1: data = self._next_data() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1316, in _next_data + 1: idx, data = self._get_data() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1272, in _get_data + 1: success, data = self._try_get_data() + 1: File "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1133, in _try_get_data + 1: raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) from e + 1: RuntimeError: DataLoader worker (pid(s) 15957) exited unexpectedly + 1: + 1: ============================================================ + 0: slurmstepd: error: *** STEP 2058110.26 ON nid005360 CANCELLED AT 2022-11-24T16:58:51 *** diff --git a/logs/2058110_119.out b/logs/2058110_119.out new file mode 100644 index 0000000000000000000000000000000000000000..9584744050f0cc28f97662d731c715693e64b1f5 --- /dev/null +++ b/logs/2058110_119.out @@ -0,0 +1,16136 @@ +25: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +10: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 4: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +12: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +16: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 9: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +22: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +26: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +19: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +21: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +30: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +28: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +14: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 2: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +21: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 3: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +21: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 1: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +10: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +21: START 2058110: Thu Nov 24 16:46:14 EET 2022 +10: START 2058110: Thu Nov 24 16:46:14 EET 2022 +23: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +20: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +18: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +24: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +13: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 0: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +31: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +17: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +29: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 5: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 7: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +15: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 8: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +11: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 6: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +27: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +25: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +25: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 4: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 4: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +25: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 4: START 2058110: Thu Nov 24 16:46:14 EET 2022 +16: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +16: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +22: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +16: START 2058110: Thu Nov 24 16:46:14 EET 2022 +22: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +22: START 2058110: Thu Nov 24 16:46:14 EET 2022 +26: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +26: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +26: START 2058110: Thu Nov 24 16:46:14 EET 2022 +12: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +12: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +12: START 2058110: Thu Nov 24 16:46:14 EET 2022 +19: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +19: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +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 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 2 34.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 4 42.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 6 43.0c 94.0W 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 ============================== +19: START 2058110: Thu Nov 24 16:46:14 EET 2022 +10: +10: +10: ======================= ROCm System Management Interface ======================= +10: ================================= Concise Info ================================= +10: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +10: 0 42.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 2 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 4 45.0c 77.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 6 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: ================================================================================ +10: ============================= End of ROCm SMI Log ============================== + 9: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 9: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +30: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +30: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 9: START 2058110: Thu Nov 24 16:46:14 EET 2022 +30: START 2058110: Thu Nov 24 16:46:14 EET 2022 +28: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +28: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +28: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 4: + 4: + 4: ======================= ROCm System Management Interface ======================= + 4: ================================= Concise Info ================================= + 4: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 4: 0 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 2 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 4 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 5 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 6 42.0c 94.0W 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 ============================== +25: +25: +25: ======================= ROCm System Management Interface ======================= +25: ================================= Concise Info ================================= +25: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +25: 0 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 2 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 4 47.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 6 39.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: ================================================================================ +25: ============================= End of ROCm SMI Log ============================== +14: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +14: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +14: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 2: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 2: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 2: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 3: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 3: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 3: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 1: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 1: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 1: START 2058110: Thu Nov 24 16:46:14 EET 2022 +23: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +23: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +23: START 2058110: Thu Nov 24 16:46:14 EET 2022 +20: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +20: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +18: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +20: START 2058110: Thu Nov 24 16:46:14 EET 2022 +18: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +18: START 2058110: Thu Nov 24 16:46:14 EET 2022 +24: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +24: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +13: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +24: START 2058110: Thu Nov 24 16:46:14 EET 2022 +13: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +13: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 0: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 0: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 0: START 2058110: Thu Nov 24 16:46:14 EET 2022 +31: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +31: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +17: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +17: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +31: START 2058110: Thu Nov 24 16:46:14 EET 2022 +17: START 2058110: Thu Nov 24 16:46:14 EET 2022 +29: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +29: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 5: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +29: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 5: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +22: +22: +22: ======================= ROCm System Management Interface ======================= +22: ================================= Concise Info ================================= +22: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +22: 0 48.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 2 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 4 44.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 6 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: ================================================================================ +22: ============================= End of ROCm SMI Log ============================== + 5: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 7: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +16: +16: +16: ======================= ROCm System Management Interface ======================= +16: ================================= Concise Info ================================= +16: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +16: 0 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 2 34.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 4 46.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 6 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: ================================================================================ +16: ============================= End of ROCm SMI Log ============================== + 7: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +26: +26: +26: ======================= ROCm System Management Interface ======================= +26: ================================= Concise Info ================================= +26: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +26: 0 50.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 2 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 4 44.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 6 40.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: ================================================================================ +26: ============================= 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 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 2 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 4 45.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 6 47.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: ================================================================================ +12: ============================= End of ROCm SMI Log ============================== + 7: START 2058110: Thu Nov 24 16:46:14 EET 2022 +15: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +15: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +19: +19: +19: ======================= ROCm System Management Interface ======================= +19: ================================= Concise Info ================================= +19: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +19: 0 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 2 46.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 4 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 6 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: ================================================================================ +19: ============================= End of ROCm SMI Log ============================== +15: START 2058110: Thu Nov 24 16:46:14 EET 2022 + 8: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 8: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 8: START 2058110: Thu Nov 24 16:46:14 EET 2022 +11: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +11: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 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 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 2 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 4 44.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 6 46.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: ================================================================================ + 9: ============================= End of ROCm SMI Log ============================== +11: START 2058110: Thu Nov 24 16:46:14 EET 2022 +30: +30: +30: ======================= ROCm System Management Interface ======================= +30: ================================= Concise Info ================================= +30: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +30: 0 45.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 2 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 4 42.0c 99.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 5 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 6 40.0c 98.0W 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 ============================== + 6: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 6: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 6: START 2058110: Thu Nov 24 16:46:14 EET 2022 +27: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +27: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +27: START 2058110: Thu Nov 24 16:46:14 EET 2022 +28: +28: +28: ======================= ROCm System Management Interface ======================= +28: ================================= Concise Info ================================= +28: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +28: 0 44.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 2 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 4 43.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 6 42.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: ================================================================================ +28: ============================= 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 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 2 37.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 4 42.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 6 44.0c 93.0W 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 ============================== +14: +14: +14: ======================= ROCm System Management Interface ======================= +14: ================================= Concise Info ================================= +14: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +14: 0 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 2 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 4 39.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 6 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: ================================================================================ +14: ============================= 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 47.0c 91.0W 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 94.0W 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 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 6 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 7 43.0c 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 44.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 1 42.0c 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 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 4 42.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 6 40.0c 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 ============================== +23: +23: +23: ======================= ROCm System Management Interface ======================= +23: ================================= Concise Info ================================= +23: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +23: 0 48.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 2 43.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 4 39.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 5 51.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 6 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: ================================================================================ +23: ============================= 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 47.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 2 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 4 46.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 6 45.0c 92.0W 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 ============================== +24: +24: +24: ======================= ROCm System Management Interface ======================= +24: ================================= Concise Info ================================= +24: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +24: 0 44.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 2 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 4 43.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 5 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 6 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: ================================================================================ +24: ============================= 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 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 2 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 3 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 4 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 6 46.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: ================================================================================ +18: ============================= 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 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 2 37.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 4 39.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 6 37.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: ================================================================================ +13: ============================= End of ROCm SMI Log ============================== + 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 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 2 38.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 4 37.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 6 37.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 7 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: ================================================================================ + 0: ============================= 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 46.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 2 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 4 44.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 6 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: ================================================================================ +31: ============================= 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 49.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 2 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 4 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 6 40.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: ================================================================================ +29: ============================= 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 46.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 2 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 4 43.0c 82.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 6 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: ================================================================================ +17: ============================= 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 90.0W 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 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 4 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 6 41.0c 88.0W 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 ============================== +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 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 1 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 2 39.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 4 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: ================================================================================ +15: ============================= 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 50.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 2 41.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 4 47.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 6 39.0c 88.0W 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 ============================== + 8: + 8: + 8: ======================= ROCm System Management Interface ======================= + 8: ================================= Concise Info ================================= + 8: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% + 8: 0 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 2 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 4 38.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 5 53.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 6 41.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: ================================================================================ + 8: ============================= 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 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 2 42.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 4 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 6 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 7 38.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: ================================================================================ + 6: ============================= 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 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 2 40.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 4 46.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 6 38.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: ================================================================================ +11: ============================= 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 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 2 42.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 4 38.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 6 48.0c 80.0W 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 ============================== +16: Launching on nid005397 (16/32), master nid005360 port 9999, GPUs 8, CUDA: True + 0: Launching on nid005360 (0/32), master nid005360 port 9999, GPUs 8, CUDA: True +25: Launching on nid005417 (25/32), master nid005360 port 9999, GPUs 8, CUDA: True +22: Launching on nid005414 (22/32), master nid005360 port 9999, GPUs 8, CUDA: True +29: Launching on nid005421 (29/32), master nid005360 port 9999, GPUs 8, CUDA: True +13: Launching on nid005373 (13/32), master nid005360 port 9999, GPUs 8, CUDA: True +19: Launching on nid005411 (19/32), master nid005360 port 9999, GPUs 8, CUDA: True + 8: Launching on nid005368 (8/32), master nid005360 port 9999, GPUs 8, CUDA: True +27: Launching on nid005419 (27/32), master nid005360 port 9999, GPUs 8, CUDA: True + 1: Launching on nid005361 (1/32), master nid005360 port 9999, GPUs 8, CUDA: True +14: Launching on nid005395 (14/32), master nid005360 port 9999, GPUs 8, CUDA: True + 4: Launching on nid005364 (4/32), master nid005360 port 9999, GPUs 8, CUDA: True +17: Launching on nid005398 (17/32), master nid005360 port 9999, GPUs 8, CUDA: True +23: Launching on nid005415 (23/32), master nid005360 port 9999, GPUs 8, CUDA: True +10: Launching on nid005370 (10/32), master nid005360 port 9999, GPUs 8, CUDA: True +31: Launching on nid005423 (31/32), master nid005360 port 9999, GPUs 8, CUDA: True + 5: Launching on nid005365 (5/32), master nid005360 port 9999, GPUs 8, CUDA: True +18: Launching on nid005399 (18/32), master nid005360 port 9999, GPUs 8, CUDA: True + 7: Launching on nid005367 (7/32), master nid005360 port 9999, GPUs 8, CUDA: True +11: Launching on nid005371 (11/32), master nid005360 port 9999, GPUs 8, CUDA: True + 2: Launching on nid005362 (2/32), master nid005360 port 9999, GPUs 8, CUDA: True +26: Launching on nid005418 (26/32), master nid005360 port 9999, GPUs 8, CUDA: True +28: Launching on nid005420 (28/32), master nid005360 port 9999, GPUs 8, CUDA: True +15: Launching on nid005396 (15/32), master nid005360 port 9999, GPUs 8, CUDA: True + 9: Launching on nid005369 (9/32), master nid005360 port 9999, GPUs 8, CUDA: True +30: Launching on nid005422 (30/32), master nid005360 port 9999, GPUs 8, CUDA: True +12: Launching on nid005372 (12/32), master nid005360 port 9999, GPUs 8, CUDA: True +20: Launching on nid005412 (20/32), master nid005360 port 9999, GPUs 8, CUDA: True +21: Launching on nid005413 (21/32), master nid005360 port 9999, GPUs 8, CUDA: True +24: Launching on nid005416 (24/32), master nid005360 port 9999, GPUs 8, CUDA: True + 3: Launching on nid005363 (3/32), master nid005360 port 9999, GPUs 8, CUDA: True + 6: Launching on nid005366 (6/32), master nid005360 port 9999, GPUs 8, CUDA: True + 0: using world size: 256, data-parallel-size: 256, 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 .............................. 256 + 0: data_path ....................................... ['/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_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/2058110.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-1 + 0: kv_channels ..................................... 64 + 0: layer_norm_fusion ............................... True + 0: layernorm_epsilon ............................... 1e-05 + 0: lazy_mpu_init ................................... None + 0: load ............................................ checkpoints_83m + 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 ............................... 0 + 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 ............................. 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_83m + 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_83m + 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 ...................................... 256 + 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: [2022-11-24 16:47:37,578] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +31: > 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: 0.073 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_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: 27.278 seconds + 0: time to initialize megatron (seconds): 50.883 + 0: [after megatron is initialized] datetime: 2022-11-24 16:48:18 + 0: building GPT model ... + 0: [2022-11-24 16:48:18,961] [INFO] [utils.py:827:see_memory_usage] Before Building Model + 0: [2022-11-24 16:48:18,962] [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: [2022-11-24 16:48:18,962] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 31.74 GB, percent = 6.3% + 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} + 0: [2022-11-24 16:48:27,708] [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: [2022-11-24 16:48:28,049] [INFO] [utils.py:827:see_memory_usage] After Building Model + 0: [2022-11-24 16:48:28,049] [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: [2022-11-24 16:48:28,049] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 31.75 GB, percent = 6.3% + 0: setting training iterations to 37905 + 0: > learning rate decay style: cosine + 0: DeepSpeed is enabled. + 0: [2022-11-24 16:48:28,051] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown + 0: [2022-11-24 16:48:46,668] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False + 0: [2022-11-24 16:48:46,668] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer + 0: [2022-11-24 16:48:46,668] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer + 0: [2022-11-24 16:48:46,671] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam + 0: [2022-11-24 16:48:46,671] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer + 0: [2022-11-24 16:48:46,714] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer + 0: [2022-11-24 16:48:46,714] [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: [2022-11-24 16:48:46,714] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.45 GB, percent = 6.4% + 4: ninja: no work to do. + 4: Time to load utils op: 0.17708468437194824 seconds + 0: ninja: no work to do. + 3: Time to load utils op: 0.11601424217224121 seconds + 3: Time to load utils op: 0.11609864234924316 seconds + 3: Time to load utils op: 0.11621832847595215 secondsTime to load utils op: 0.11625456809997559 seconds + 3: Time to load utils op: 0.1162266731262207 seconds + 3: + 3: Time to load utils op: 0.11626839637756348 seconds + 3: Time to load utils op: 0.11626553535461426 secondsTime to load utils op: 0.11624693870544434 seconds + 3: + 7: Time to load utils op: 0.12700867652893066 seconds + 7: Time to load utils op: 0.12777209281921387 seconds + 7: Time to load utils op: 0.12772297859191895 seconds + 7: Time to load utils op: 0.127913236618042 secondsTime to load utils op: 0.12756681442260742 seconds + 7: + 7: Time to load utils op: 0.3271341323852539 secondsTime to load utils op: 0.12742066383361816 seconds + 7: + 0: Time to load utils op: 0.15517687797546387 secondsTime to load utils op: 0.3155193328857422 seconds + 0: + 8: Time to load utils op: 0.14496707916259766 seconds + 8: Time to load utils op: 0.14435553550720215 seconds + 8: Time to load utils op: 0.14549040794372559 seconds + 8: Time to load utils op: 0.14443707466125488 seconds + 8: Time to load utils op: 0.14553284645080566 secondsTime to load utils op: 0.1457219123840332 secondsTime to load utils op: 0.14519882202148438 secondsTime to load utils op: 0.14483428001403809 seconds + 8: + 8: + 8: + 6: Time to load utils op: 0.14590668678283691 secondsTime to load utils op: 0.14591073989868164 seconds + 6: + 6: Time to load utils op: 0.14593815803527832 seconds + 6: Time to load utils op: 0.14595603942871094 seconds + 6: Time to load utils op: 0.1459643840789795 secondsTime to load utils op: 0.145965576171875 secondsTime to load utils op: 0.14595961570739746 seconds + 6: + 6: + 6: Time to load utils op: 0.14600419998168945 seconds + 5: Time to load utils op: 0.14726996421813965 seconds + 5: Time to load utils op: 0.1473560333251953 seconds + 5: Time to load utils op: 0.14739084243774414 secondsTime to load utils op: 0.14739131927490234 seconds + 5: Time to load utils op: 0.14742493629455566 seconds + 5: + 5: Time to load utils op: 0.14744186401367188 seconds + 5: Time to load utils op: 0.14751839637756348 secondsTime to load utils op: 0.14750051498413086 seconds + 5: +16: Time to load utils op: 0.13729500770568848 secondsTime to load utils op: 0.1372973918914795 seconds +16: +16: Time to load utils op: 0.13730716705322266 seconds +16: Time to load utils op: 0.13731718063354492 seconds +16: Time to load utils op: 0.1373615264892578 seconds +16: Time to load utils op: 0.13737010955810547 seconds +16: Time to load utils op: 0.13736939430236816 seconds +16: Time to load utils op: 0.1374502182006836 seconds +15: Time to load utils op: 0.1429305076599121 seconds +15: Time to load utils op: 0.14311552047729492 secondsTime to load utils op: 0.14341402053833008 seconds +15: +15: Time to load utils op: 0.1434311866760254 seconds +15: Time to load utils op: 0.3444797992706299 seconds +15: Time to load utils op: 0.1437084674835205 seconds +15: Time to load utils op: 0.14346814155578613 secondsTime to load utils op: 0.1438133716583252 seconds +15: +19: Time to load utils op: 0.13953089714050293 secondsTime to load utils op: 0.1404881477355957 secondsTime to load utils op: 0.1403672695159912 seconds +19: +19: +19: Time to load utils op: 0.14014077186584473 seconds +19: Time to load utils op: 0.14109420776367188 secondsTime to load utils op: 0.1396772861480713 seconds +19: +19: Time to load utils op: 0.14025545120239258 seconds +19: Time to load utils op: 0.14082789421081543 seconds +17: Time to load utils op: 0.13805294036865234 seconds +21: Time to load utils op: 0.13415122032165527 seconds +17: Time to load utils op: 0.13831496238708496 secondsTime to load utils op: 0.138322114944458 seconds +17: +17: Time to load utils op: 0.13832950592041016 seconds +17: Time to load utils op: 0.13834071159362793 seconds +21: Time to load utils op: 0.13420438766479492 seconds +17: Time to load utils op: 0.13834881782531738 seconds +21: Time to load utils op: 0.13423395156860352 seconds +17: Time to load utils op: 0.13846492767333984 seconds +30: Time to load utils op: 0.12216401100158691 secondsTime to load utils op: 0.12218475341796875 seconds +30: +30: Time to load utils op: 0.12219834327697754 secondsTime to load utils op: 0.12221026420593262 seconds +30: Time to load utils op: 0.12221336364746094 seconds +30: +21: Time to load utils op: 0.13427352905273438 seconds +21: Time to load utils op: 0.13429832458496094 seconds +17: Time to load utils op: 0.13850975036621094 seconds +21: Time to load utils op: 0.1343522071838379 secondsTime to load utils op: 0.13437390327453613 seconds +21: +30: Time to load utils op: 0.12223291397094727 secondsTime to load utils op: 0.12221789360046387 seconds +30: +21: Time to load utils op: 0.13450980186462402 seconds +30: Time to load utils op: 0.12225770950317383 seconds +10: Time to load utils op: 0.1536097526550293 secondsTime to load utils op: 0.15436029434204102 seconds +10: +24: Time to load utils op: 0.13448357582092285 seconds +24: Time to load utils op: 0.13433313369750977 seconds +24: Time to load utils op: 0.1347808837890625 seconds +10: Time to load utils op: 0.15385198593139648 seconds +24: Time to load utils op: 0.13492512702941895 seconds +10: Time to load utils op: 0.1535172462463379 seconds +10: Time to load utils op: 0.15333342552185059 secondsTime to load utils op: 0.1542823314666748 seconds +10: +24: Time to load utils op: 0.13518786430358887 seconds +24: Time to load utils op: 0.13525962829589844 secondsTime to load utils op: 0.13480138778686523 seconds +24: +10: Time to load utils op: 0.1548328399658203 seconds +10: Time to load utils op: 0.1542038917541504 seconds +12: Time to load utils op: 0.14644289016723633 seconds +12: Time to load utils op: 0.14647507667541504 seconds +12: Time to load utils op: 0.14647293090820312 seconds +24: Time to load utils op: 0.33760643005371094 seconds +12: Time to load utils op: 0.14649510383605957 secondsTime to load utils op: 0.14652419090270996 seconds +12: +12: Time to load utils op: 0.14653253555297852 seconds +12: Time to load utils op: 0.14655017852783203 secondsTime to load utils op: 0.14653730392456055 seconds +12: +18: Time to load utils op: 0.14335298538208008 seconds +23: Time to load utils op: 0.13634371757507324 secondsTime to load utils op: 0.13624191284179688 seconds +23: +18: Time to load utils op: 0.14327621459960938 seconds +18: Time to load utils op: 0.14335989952087402 seconds +18: Time to load utils op: 0.14354848861694336 seconds +18: Time to load utils op: 0.3456759452819824 secondsTime to load utils op: 0.14377093315124512 seconds +18: +18: Time to load utils op: 0.14340615272521973 seconds +18: Time to load utils op: 0.14334821701049805 seconds +23: Time to load utils op: 0.13701438903808594 secondsTime to load utils op: 0.1370222568511963 seconds +23: +23: Time to load utils op: 0.13665485382080078 secondsTime to load utils op: 0.13657522201538086 seconds +23: +13: Time to load utils op: 0.1468040943145752 seconds +23: Time to load utils op: 0.13694286346435547 seconds +23: Time to load utils op: 0.3393666744232178 seconds +13: Time to load utils op: 0.14685726165771484 seconds +13: Time to load utils op: 0.14688849449157715 seconds +13: Time to load utils op: 0.14688515663146973 secondsTime to load utils op: 0.14688539505004883 seconds +13: +13: Time to load utils op: 0.14690351486206055 secondsTime to load utils op: 0.14693307876586914 secondsTime to load utils op: 0.14690041542053223 seconds +13: +13: +11: Time to load utils op: 0.153411865234375 secondsTime to load utils op: 0.15296483039855957 seconds +11: +11: Time to load utils op: 0.1534419059753418 seconds +11: Time to load utils op: 0.15268874168395996 seconds +11: Time to load utils op: 0.15269923210144043 secondsTime to load utils op: 0.15274572372436523 secondsTime to load utils op: 0.15274620056152344 seconds +11: +11: +11: Time to load utils op: 0.15272760391235352 seconds +20: Time to load utils op: 0.13745641708374023 seconds +20: Time to load utils op: 0.1374659538269043 seconds +20: Time to load utils op: 0.137481689453125 seconds +20: Time to load utils op: 0.13753461837768555 seconds +20: Time to load utils op: 0.13750123977661133 secondsTime to load utils op: 0.1375572681427002 seconds +20: +20: Time to load utils op: 0.13755583763122559 seconds +20: Time to load utils op: 0.13753771781921387 seconds +14: Time to load utils op: 0.15096664428710938 secondsTime to load utils op: 0.15097522735595703 seconds +14: +14: Time to load utils op: 0.15092039108276367 seconds +14: Time to load utils op: 0.15152335166931152 secondsTime to load utils op: 0.15031909942626953 seconds +14: +22: Time to load utils op: 0.1361558437347412 seconds +14: Time to load utils op: 0.15049171447753906 seconds +26: Time to load utils op: 0.13489651679992676 seconds +14: Time to load utils op: 0.1504826545715332 seconds +14: Time to load utils op: 0.15019774436950684 seconds +22: Time to load utils op: 0.1361548900604248 seconds +22: Time to load utils op: 0.13616156578063965 seconds +22: Time to load utils op: 0.1362152099609375 seconds +22: Time to load utils op: 0.13622760772705078 secondsTime to load utils op: 0.13623046875 seconds +22: +22: Time to load utils op: 0.13623332977294922 secondsTime to load utils op: 0.1362297534942627 seconds +22: +26: Time to load utils op: 0.13396310806274414 seconds +26: Time to load utils op: 0.13511180877685547 secondsTime to load utils op: 0.1347517967224121 seconds +26: +27: Time to load utils op: 0.12834429740905762 seconds +27: Time to load utils op: 0.12833070755004883 seconds +26: Time to load utils op: 0.13502764701843262 seconds +26: Time to load utils op: 0.13512611389160156 seconds +26: Time to load utils op: 0.1341254711151123 secondsTime to load utils op: 0.13462090492248535 seconds +26: +27: Time to load utils op: 0.1284017562866211 seconds +27: Time to load utils op: 0.12842416763305664 seconds +31: Time to load utils op: 0.12362456321716309 seconds +27: Time to load utils op: 0.12842416763305664 secondsTime to load utils op: 0.12843608856201172 seconds +27: +27: Time to load utils op: 0.12841320037841797 seconds +27: Time to load utils op: 0.12847304344177246 seconds +31: Time to load utils op: 0.12364721298217773 seconds +31: Time to load utils op: 0.12368392944335938 seconds +31: Time to load utils op: 0.12370085716247559 secondsTime to load utils op: 0.12369012832641602 seconds +31: +31: Time to load utils op: 0.1237022876739502 seconds +31: Time to load utils op: 0.12372922897338867 seconds +31: Time to load utils op: 0.12371683120727539 seconds +29: Time to load utils op: 0.12737131118774414 secondsTime to load utils op: 0.12736201286315918 secondsTime to load utils op: 0.12734675407409668 secondsTime to load utils op: 0.1273491382598877 seconds +29: +29: +29: +29: Time to load utils op: 0.12736272811889648 seconds +29: Time to load utils op: 0.127485990524292 secondsTime to load utils op: 0.1275181770324707 seconds +29: +29: Time to load utils op: 0.12752676010131836 seconds +25: Time to load utils op: 0.13324618339538574 seconds +25: Time to load utils op: 0.13322782516479492 seconds +25: Time to load utils op: 0.13324642181396484 seconds +25: Time to load utils op: 0.13326811790466309 secondsTime to load utils op: 0.1332552433013916 seconds +25: Time to load utils op: 0.1332552433013916 seconds +25: Time to load utils op: 0.13326454162597656 seconds +25: +25: Time to load utils op: 0.1332705020904541 seconds + 9: Time to load utils op: 0.15452337265014648 secondsTime to load utils op: 0.1545546054840088 secondsTime to load utils op: 0.1545543670654297 seconds + 9: + 9: + 9: Time to load utils op: 0.15456819534301758 seconds + 9: Time to load utils op: 0.15456318855285645 seconds +28: Time to load utils op: 0.12966537475585938 seconds +28: Time to load utils op: 0.12964653968811035 seconds +28: Time to load utils op: 0.12966084480285645 seconds + 9: Time to load utils op: 0.15457701683044434 seconds + 9: Time to load utils op: 0.1545724868774414 seconds + 9: Time to load utils op: 0.15459895133972168 seconds +28: Time to load utils op: 0.12967300415039062 seconds +28: Time to load utils op: 0.12972545623779297 seconds +28: Time to load utils op: 0.12970399856567383 secondsTime to load utils op: 0.12970614433288574 seconds +28: +28: Time to load utils op: 0.12971973419189453 seconds + 0: [2022-11-24 16:48:47,072] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 + 0: [2022-11-24 16:48:47,073] [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: [2022-11-24 16:48:47,073] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.46 GB, percent = 6.4% + 0: Time to load utils op: 0.20273232460021973 seconds + 0: Time to load utils op: 0.20279455184936523 seconds + 0: Time to load utils op: 0.2019975185394287 seconds + 0: Time to load utils op: 0.20264458656311035 seconds + 0: Time to load utils op: 0.20212078094482422 seconds + 0: Time to load utils op: 0.20218539237976074 seconds + 4: Time to load utils op: 0.20360946655273438 seconds + 4: Time to load utils op: 0.20368170738220215 seconds + 4: Time to load utils op: 0.20443964004516602 seconds + 4: Time to load utils op: 0.20513439178466797 seconds + 4: Time to load utils op: 0.20534348487854004 seconds + 4: Time to load utils op: 0.20382976531982422 seconds + 4: Time to load utils op: 0.20466899871826172 seconds + 7: Time to load utils op: 0.2027416229248047 seconds + 3: Time to load utils op: 0.0006225109100341797 seconds + 3: Time to load utils op: 0.0006654262542724609 seconds + 3: Time to load utils op: 0.00048160552978515625 seconds + 3: Time to load utils op: 0.0005125999450683594 seconds + 3: Time to load utils op: 0.00038313865661621094 seconds + 3: Time to load utils op: 0.00046944618225097656 seconds + 3: Time to load utils op: 0.0005297660827636719 seconds + 3: Time to load utils op: 0.0005877017974853516 seconds + 1: Time to load utils op: 0.21785259246826172 seconds + 1: Time to load utils op: 0.2180500030517578 seconds + 1: Time to load utils op: 0.21805572509765625 seconds + 1: Time to load utils op: 0.21825242042541504 seconds + 1: Time to load utils op: 0.21827125549316406 seconds + 1: Time to load utils op: 0.21838760375976562 seconds + 1: Time to load utils op: 0.21842694282531738 secondsTime to load utils op: 0.21840143203735352 seconds + 1: + 2: Time to load utils op: 0.21813321113586426 seconds + 2: Time to load utils op: 0.21816205978393555 seconds + 2: Time to load utils op: 0.2181856632232666 seconds + 2: Time to load utils op: 0.21822118759155273 seconds + 2: Time to load utils op: 0.2183074951171875 seconds + 2: Time to load utils op: 0.21835041046142578 seconds + 2: Time to load utils op: 0.21836137771606445 seconds + 2: Time to load utils op: 0.21844220161437988 seconds +24: Time to load utils op: 0.0005009174346923828 seconds + 6: Time to load utils op: 0.0007183551788330078 seconds + 6: Time to load utils op: 0.0008821487426757812 seconds + 6: Time to load utils op: 0.0009953975677490234 seconds + 6: Time to load utils op: 0.0009686946868896484 seconds + 6: Time to load utils op: 0.0009870529174804688 seconds + 6: Time to load utils op: 0.001033782958984375 seconds + 6: Time to load utils op: 0.0007448196411132812 seconds + 6: Time to load utils op: 0.0010640621185302734 seconds + 0: Time to load utils op: 0.00044655799865722656 seconds + 0: Time to load utils op: 0.0004749298095703125 seconds + 0: Time to load utils op: 0.000446319580078125 seconds + 0: Time to load utils op: 0.0004405975341796875 seconds + 0: Time to load utils op: 0.00044226646423339844 seconds + 0: Time to load utils op: 0.0004475116729736328 seconds + 0: Time to load utils op: 0.0005106925964355469 seconds +18: Time to load utils op: 0.00075531005859375 seconds +18: Time to load utils op: 0.0005426406860351562 seconds +18: Time to load utils op: 0.0005679130554199219 seconds +18: Time to load utils op: 0.0008511543273925781 seconds +18: Time to load utils op: 0.0005943775177001953 secondsTime to load utils op: 0.0005137920379638672 seconds +18: +18: Time to load utils op: 0.0005307197570800781 seconds +18: Time to load utils op: 0.0008978843688964844 seconds + 5: Time to load utils op: 0.0008461475372314453 seconds +30: Time to load utils op: 0.0006594657897949219 seconds + 5: Time to load utils op: 0.000995635986328125 seconds + 5: Time to load utils op: 0.001058340072631836 seconds + 5: Time to load utils op: 0.001195669174194336 secondsTime to load utils op: 0.0011115074157714844 seconds + 5: +30: Time to load utils op: 0.0005331039428710938 seconds + 5: Time to load utils op: 0.001251220703125 seconds + 5: Time to load utils op: 0.0012450218200683594 seconds + 5: Time to load utils op: 0.0013458728790283203 seconds +30: Time to load utils op: 0.0006711483001708984 secondsTime to load utils op: 0.0004971027374267578 seconds +30: Time to load utils op: 0.00041031837463378906 seconds +30: Time to load utils op: 0.00039887428283691406 seconds +30: +30: Time to load utils op: 0.0003838539123535156 seconds +30: Time to load utils op: 0.0003426074981689453 seconds +19: Time to load utils op: 0.0008356571197509766 seconds +14: Time to load utils op: 0.0006852149963378906 seconds +14: Time to load utils op: 0.0006647109985351562 seconds +14: Time to load utils op: 0.0003542900085449219 seconds +19: Time to load utils op: 0.0013628005981445312 seconds +19: Time to load utils op: 0.0013082027435302734 seconds +19: Time to load utils op: 0.0013000965118408203 seconds +14: Time to load utils op: 0.00034308433532714844 seconds +19: Time to load utils op: 0.0013349056243896484 secondsTime to load utils op: 0.0013065338134765625 seconds +19: +19: Time to load utils op: 0.0013110637664794922 seconds +14: Time to load utils op: 0.0003590583801269531 seconds +14: Time to load utils op: 0.00041222572326660156 secondsTime to load utils op: 0.00041484832763671875 seconds +14: +19: Time to load utils op: 0.0013556480407714844 seconds +14: Time to load utils op: 0.00044465065002441406 seconds +20: Time to load utils op: 0.0006361007690429688 seconds +20: Time to load utils op: 0.0006611347198486328 seconds +20: Time to load utils op: 0.0004029273986816406 seconds +20: Time to load utils op: 0.0004608631134033203 seconds +20: Time to load utils op: 0.000644683837890625 seconds +20: Time to load utils op: 0.0007281303405761719 seconds +20: Time to load utils op: 0.0007371902465820312 seconds + 2: Time to load utils op: 0.0010793209075927734 seconds + 2: Time to load utils op: 0.0013005733489990234 seconds +20: Time to load utils op: 0.0007424354553222656 seconds +31: Time to load utils op: 0.0011219978332519531 seconds + 2: Time to load utils op: 0.0012559890747070312 seconds + 2: Time to load utils op: 0.0014624595642089844 seconds + 2: Time to load utils op: 0.0014941692352294922 seconds + 2: Time to load utils op: 0.001378774642944336 seconds +28: Time to load utils op: 0.0007712841033935547 seconds + 2: Time to load utils op: 0.0013756752014160156 seconds + 2: Time to load utils op: 0.001329183578491211 seconds +17: Time to load utils op: 0.0006861686706542969 seconds +28: Time to load utils op: 0.0008535385131835938 seconds +31: Time to load utils op: 0.0012233257293701172 seconds +31: Time to load utils op: 0.0013387203216552734 seconds +28: Time to load utils op: 0.00087738037109375 seconds +31: Time to load utils op: 0.0013499259948730469 seconds +29: Time to load utils op: 0.0006382465362548828 seconds +31: Time to load utils op: 0.0013713836669921875 seconds +15: Time to load utils op: 0.0009982585906982422 seconds +17: Time to load utils op: 0.00058746337890625 seconds +29: Time to load utils op: 0.0007512569427490234 secondsTime to load utils op: 0.0004987716674804688 seconds +29: +31: Time to load utils op: 0.0013813972473144531 seconds +31: Time to load utils op: 0.0011987686157226562 seconds +31: Time to load utils op: 0.0013689994812011719 seconds +28: Time to load utils op: 0.000934600830078125 secondsTime to load utils op: 0.0010402202606201172 secondsTime to load utils op: 0.0008528232574462891 seconds +28: +28: +28: Time to load utils op: 0.001102447509765625 seconds +29: Time to load utils op: 0.0006892681121826172 seconds +29: Time to load utils op: 0.0006597042083740234 seconds +29: Time to load utils op: 0.0008661746978759766 secondsTime to load utils op: 0.0007770061492919922 seconds +29: +17: Time to load utils op: 0.00037288665771484375 seconds +28: Time to load utils op: 0.0010721683502197266 seconds +29: Time to load utils op: 0.0009703636169433594 seconds +15: Time to load utils op: 0.0012845993041992188 seconds +15: Time to load utils op: 0.001226663589477539 secondsTime to load utils op: 0.0013134479522705078 secondsTime to load utils op: 0.0012278556823730469 seconds +15: +15: +17: Time to load utils op: 0.0006208419799804688 secondsTime to load utils op: 0.00040841102600097656 seconds +17: Time to load utils op: 0.00048089027404785156 seconds +17: +15: Time to load utils op: 0.0012292861938476562 seconds +15: Time to load utils op: 0.0012519359588623047 seconds +17: Time to load utils op: 0.0005898475646972656 seconds +15: Time to load utils op: 0.0012640953063964844 seconds +17: Time to load utils op: 0.0004405975341796875 seconds +10: Time to load utils op: 0.0006566047668457031 seconds +10: Time to load utils op: 0.0006957054138183594 seconds +10: Time to load utils op: 0.00045418739318847656 seconds +10: Time to load utils op: 0.0004553794860839844 seconds +10: Time to load utils op: 0.0005128383636474609 secondsTime to load utils op: 0.000415802001953125 seconds +10: +10: Time to load utils op: 0.0004889965057373047 seconds +10: Time to load utils op: 0.0004954338073730469 seconds +13: Time to load utils op: 0.0007350444793701172 seconds +13: Time to load utils op: 0.0004532337188720703 seconds +13: Time to load utils op: 0.0004391670227050781 seconds +13: Time to load utils op: 0.0009684562683105469 seconds +13: Time to load utils op: 0.0009961128234863281 seconds +13: Time to load utils op: 0.0009813308715820312 seconds +13: Time to load utils op: 0.0010597705841064453 seconds +13: Time to load utils op: 0.0007081031799316406 seconds +26: Time to load utils op: 0.0009002685546875 seconds +26: Time to load utils op: 0.0013873577117919922 seconds +26: Time to load utils op: 0.0013957023620605469 seconds +26: Time to load utils op: 0.001407623291015625 secondsTime to load utils op: 0.0013422966003417969 seconds +26: +26: Time to load utils op: 0.0012769699096679688 seconds +26: Time to load utils op: 0.0014882087707519531 seconds +26: Time to load utils op: 0.001359701156616211 seconds + 0: [2022-11-24 16:48:47,171] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 + 0: [2022-11-24 16:48:47,172] [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: [2022-11-24 16:48:47,173] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.58 GB, percent = 6.5% +24: Time to load utils op: 0.000415802001953125 secondsTime to load utils op: 0.00035762786865234375 seconds +24: +24: Time to load utils op: 0.00038814544677734375 seconds +24: Time to load utils op: 0.0003902912139892578 seconds +24: Time to load utils op: 0.00041484832763671875 seconds +24: Time to load utils op: 0.00039386749267578125 seconds +24: Time to load utils op: 0.0003886222839355469 seconds + 0: [2022-11-24 16:48:47,212] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 + 0: [2022-11-24 16:48:47,213] [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: [2022-11-24 16:48:47,213] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.6 GB, percent = 6.5% + 0: [2022-11-24 16:48:47,246] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 + 0: [2022-11-24 16:48:47,247] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 16:48:47,247] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.6 GB, percent = 6.5% + 0: [2022-11-24 16:48:47,278] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 + 0: [2022-11-24 16:48:47,278] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 16:48:47,278] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.6 GB, percent = 6.5% + 0: [2022-11-24 16:48:47,311] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 + 0: [2022-11-24 16:48:47,312] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 16:48:47,312] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.6 GB, percent = 6.5% + 0: [2022-11-24 16:48:47,342] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer + 0: [2022-11-24 16:48:47,342] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 16:48:47,343] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.6 GB, percent = 6.5% + 0: [2022-11-24 16:48:47,378] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer + 0: [2022-11-24 16:48:47,379] [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: [2022-11-24 16:48:47,379] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.6 GB, percent = 6.5% + 0: [2022-11-24 16:48:47,409] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer + 0: [2022-11-24 16:48:47,410] [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: [2022-11-24 16:48:47,410] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.6 GB, percent = 6.5% + 0: [2022-11-24 16:48:47,410] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam + 0: [2022-11-24 16:48:47,410] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler + 0: [2022-11-24 16:48:47,410] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = + 0: [2022-11-24 16:48:47,410] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0002, 0.0002, 0.0002], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: [2022-11-24 16:48:47,410] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: + 0: [2022-11-24 16:48:47,410] [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: [2022-11-24 16:48:47,410] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] amp_enabled .................. False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] amp_params ................... False + 0: [2022-11-24 16:48:47,411] [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: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] bfloat16_enabled ............. True + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] comms_config ................. + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] communication_data_type ...... None + 0: [2022-11-24 16:48:47,411] [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: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] curriculum_enabled ........... False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] curriculum_params ............ False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] dataloader_drop_last ......... False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] disable_allgather ............ False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] dump_state ................... False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] elasticity_enabled ........... False + 0: [2022-11-24 16:48:47,411] [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: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] fp16_auto_cast ............... None + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] fp16_enabled ................. False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] global_rank .................. 0 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 + 0: [2022-11-24 16:48:47,411] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] load_universal_checkpoint .... False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] loss_scale ................... 1.0 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] memory_breakdown ............. False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] monitor_config ............... + 0: [2022-11-24 16:48:47,412] [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: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] optimizer_name ............... None + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] optimizer_params ............. None + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] pld_enabled .................. False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] pld_params ................... False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] prescale_gradients ........... False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] scheduler_name ............... None + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] scheduler_params ............. None + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] sparse_attention ............. None + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] steps_per_print .............. 2000 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] train_batch_size ............. 256 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 1 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] use_node_local_storage ....... False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] world_size ................... 256 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False + 0: [2022-11-24 16:48:47,412] [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: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] zero_enabled ................. False + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 + 0: [2022-11-24 16:48:47,412] [INFO] [config.py:996:print_user_config] json = { + 0: "train_micro_batch_size_per_gpu": 1, + 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: 0.00040435791015625 seconds + 0: [2022-11-24 16:48:47,413] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=1 +11: Time to load utils op: 0.0010144710540771484 seconds +11: Time to load utils op: 0.0010755062103271484 seconds + 8: Time to load utils op: 0.0009655952453613281 seconds +11: Time to load utils op: 0.0015628337860107422 seconds +11: Time to load utils op: 0.001543283462524414 seconds +11: Time to load utils op: 0.0015447139739990234 seconds + 8: Time to load utils op: 0.0012848377227783203 seconds +11: Time to load utils op: 0.001585245132446289 seconds +11: Time to load utils op: 0.0015468597412109375 secondsTime to load utils op: 0.0015478134155273438 seconds +11: +27: Time to load utils op: 0.0006952285766601562 seconds + 7: Time to load utils op: 0.0004968643188476562 seconds +27: Time to load utils op: 0.0007481575012207031 seconds + 8: Time to load utils op: 0.0014843940734863281 seconds + 8: Time to load utils op: 0.001421213150024414 secondsTime to load utils op: 0.0014312267303466797 seconds + 8: Time to load utils op: 0.0014040470123291016 seconds +23: Time to load utils op: 0.0005233287811279297 secondsTime to load utils op: 0.0004851818084716797 seconds +23: + 7: Time to load utils op: 0.0005857944488525391 seconds + 7: Time to load utils op: 0.0005910396575927734 seconds + 8: +12: Time to load utils op: 0.0009622573852539062 seconds + 7: Time to load utils op: 0.000568389892578125 seconds + 8: Time to load utils op: 0.0014216899871826172 seconds +27: Time to load utils op: 0.0007836818695068359 seconds + 8: Time to load utils op: 0.0015048980712890625 seconds +27: Time to load utils op: 0.0005342960357666016 secondsTime to load utils op: 0.00040268898010253906 seconds +27: +27: Time to load utils op: 0.00047659873962402344 seconds + 1: Time to load utils op: 0.0007529258728027344 seconds +23: Time to load utils op: 0.0005869865417480469 secondsTime to load utils op: 0.0005724430084228516 seconds +23: + 7: Time to load utils op: 0.0005981922149658203 seconds +16: Time to load utils op: 0.0009100437164306641 seconds +22: Time to load utils op: 0.0009183883666992188 seconds +23: Time to load utils op: 0.0005908012390136719 seconds + 7: Time to load utils op: 0.0006098747253417969 seconds + 1: Time to load utils op: 0.0007910728454589844 seconds +27: Time to load utils op: 0.0005438327789306641 seconds + 7: Time to load utils op: 0.0006539821624755859 seconds + 7: Time to load utils op: 0.00066375732421875 seconds +22: Time to load utils op: 0.001085519790649414 seconds +23: Time to load utils op: 0.0007207393646240234 secondsTime to load utils op: 0.0007193088531494141 secondsTime to load utils op: 0.0006747245788574219 seconds +23: +23: +27: Time to load utils op: 0.0005168914794921875 seconds +12: Time to load utils op: 0.0014524459838867188 seconds + 1: Time to load utils op: 0.001184225082397461 seconds +22: Time to load utils op: 0.0014460086822509766 seconds +22: Time to load utils op: 0.0014126300811767578 secondsTime to load utils op: 0.001402139663696289 seconds +22: + 1: Time to load utils op: 0.0013415813446044922 secondsTime to load utils op: 0.0013861656188964844 seconds + 1: + 1: Time to load utils op: 0.001348733901977539 seconds +16: Time to load utils op: 0.0014717578887939453 seconds +22: Time to load utils op: 0.0014348030090332031 seconds +22: Time to load utils op: 0.0014390945434570312 seconds +12: Time to load utils op: 0.0015676021575927734 seconds +22: Time to load utils op: 0.0014925003051757812 seconds +12: Time to load utils op: 0.0015816688537597656 seconds +12: Time to load utils op: 0.0015494823455810547 seconds + 1: Time to load utils op: 0.0013570785522460938 seconds +16: Time to load utils op: 0.0014388561248779297 seconds + 9: Time to load utils op: 0.0011565685272216797 seconds + 1: Time to load utils op: 0.0014584064483642578 seconds +16: Time to load utils op: 0.0014925003051757812 secondsTime to load utils op: 0.001434326171875 seconds +16: Time to load utils op: 0.0015106201171875 seconds +16: + 4: Time to load utils op: 0.0005009174346923828 seconds +12: Time to load utils op: 0.0015642642974853516 seconds +16: Time to load utils op: 0.0014414787292480469 seconds + 4: Time to load utils op: 0.0005171298980712891 seconds + 4: Time to load utils op: 0.0005049705505371094 seconds +12: Time to load utils op: 0.001522064208984375 seconds +16: Time to load utils op: 0.0015637874603271484 seconds +12: Time to load utils op: 0.0016036033630371094 seconds + 4: Time to load utils op: 0.0005426406860351562 secondsTime to load utils op: 0.0005297660827636719 secondsTime to load utils op: 0.0005717277526855469 secondsTime to load utils op: 0.0005619525909423828 seconds + 4: + 4: + 4: + 4: Time to load utils op: 0.0004467964172363281 seconds + 9: Time to load utils op: 0.0013699531555175781 seconds + 9: Time to load utils op: 0.0013728141784667969 seconds + 9: Time to load utils op: 0.001461029052734375 seconds + 9: Time to load utils op: 0.0013828277587890625 seconds + 9: Time to load utils op: 0.0014736652374267578 secondsTime to load utils op: 0.0013895034790039062 seconds + 9: + 9: Time to load utils op: 0.001505136489868164 seconds +21: Time to load utils op: 0.0008704662322998047 seconds +21: Time to load utils op: 0.001149892807006836 seconds +21: Time to load utils op: 0.001386404037475586 secondsTime to load utils op: 0.0013637542724609375 seconds +21: Time to load utils op: 0.0013802051544189453 seconds +21: +21: Time to load utils op: 0.001371622085571289 seconds +21: Time to load utils op: 0.001356363296508789 seconds +21: Time to load utils op: 0.0013692378997802734 seconds +25: Time to load utils op: 0.0010380744934082031 seconds +25: Time to load utils op: 0.0010843276977539062 seconds +25: Time to load utils op: 0.0013189315795898438 seconds +25: Time to load utils op: 0.0012736320495605469 seconds +25: Time to load utils op: 0.0012936592102050781 seconds +25: Time to load utils op: 0.0013284683227539062 seconds +25: Time to load utils op: 0.0013344287872314453 seconds +25: Time to load utils op: 0.0013356208801269531 seconds + 0: [2022-11-24 16:48:47,460] [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: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,506] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,507] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,508] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,509] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,510] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,511] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,529] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 16:48:47,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,531] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,532] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,534] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,535] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,536] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,538] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,539] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,540] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,541] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,542] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,543] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,544] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,545] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,546] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,533] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,569] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 16:48:47,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 16:48:47,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 16:48:47,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 16:48:47,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,570] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,590] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,591] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,620] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,624] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 16:48:47,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,621] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 16:48:47,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 16:48:47,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 16:48:47,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,592] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 16:48:47,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 16:48:47,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 16:48:47,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,625] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,593] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,622] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,623] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 16:48:47,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 16:48:47,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 16:48:47,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,263] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 97 + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 99 + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,351] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 98 + 4: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 16:48:48,358] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 103 + 4: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 100 + 4: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 101 + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,368] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 102 + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,381] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 96 + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +12: [2022-11-24 16:48:48,419] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 98 + 4: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:48:48,436] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 97 + 4: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:48:48,439] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 96 + 4: [2022-11-24 16:48:48,345] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 39 +12: [2022-11-24 16:48:48,451] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 99 + 4: [2022-11-24 16:48:48,345] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 35 +12: [2022-11-24 16:48:48,651] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 103 + 4: [2022-11-24 16:48:48,346] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:48:48,653] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 101 + 4: [2022-11-24 16:48:48,347] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 36 +12: [2022-11-24 16:48:48,654] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 100 + 4: [2022-11-24 16:48:48,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +12: [2022-11-24 16:48:48,661] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 102 + 4: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 32 + 5: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,357] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 38 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,359] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 33 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 37 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 34 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,467] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 36 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,485] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 35 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,497] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 32 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,498] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 39 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,499] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 38 + 5: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 16:48:48,513] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 33 + 5: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,542] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 37 + 5: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 16:48:48,585] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 34 + 5: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,145] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,224] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:48:48,316] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:48:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,317] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:48,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,332] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 47 + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,332] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 45 + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,332] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 43 + 7: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,334] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 41 + 7: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:48:48,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:48:48,335] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 40 + 7: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:48:48,335] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 46 + 7: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:48:48,335] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 44 + 7: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 5: [2022-11-24 16:48:48,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 7: [2022-11-24 16:48:48,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:48,346] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 42 + 7: [2022-11-24 16:48:48,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:48,370] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 47 + 7: [2022-11-24 16:48:48,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:48,407] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 45 + 7: [2022-11-24 16:48:48,342] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 56 + 5: [2022-11-24 16:48:48,410] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 42 + 7: [2022-11-24 16:48:48,342] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 60 + 5: [2022-11-24 16:48:48,517] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 43 + 7: [2022-11-24 16:48:48,342] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 58 + 5: [2022-11-24 16:48:48,586] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 46 + 7: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:48,588] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 40 + 7: [2022-11-24 16:48:48,351] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 59 + 5: [2022-11-24 16:48:48,598] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 44 + 7: [2022-11-24 16:48:48,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 5: [2022-11-24 16:48:48,610] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 41 + 7: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 63 + 7: [2022-11-24 16:48:48,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,354] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 62 + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,355] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 61 + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 57 + 0: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,461] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 57 + 0: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,469] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 63 + 0: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,491] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 62 + 0: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,502] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 60 + 0: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,511] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 56 + 0: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 16:48:48,519] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 61 + 0: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,536] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 58 + 0: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 16:48:48,548] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 59 + 0: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,994] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,994] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:47,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,104] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,106] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,107] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,165] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,168] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,169] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,264] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,264] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,265] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,265] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: > using checkpoint value 0.0002 for learning rate + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: > using checkpoint value 2e-05 for minimum learning rate + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: > using checkpoint value 0 for warmup iterations + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: > using checkpoint value 9703701 for total number of iterations + 0: > using checkpoint value cosine for decay style + 2: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,348] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 4 + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,358] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 4 + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 16:48:48,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 6 + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,369] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 3 + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,371] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 0 + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 2: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... + 0: [2022-11-24 16:48:48,372] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 1 + 2: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:48,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:48,373] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 2 + 2: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 18 + 0: [2022-11-24 16:48:48,392] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 6 + 2: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 19 + 0: [2022-11-24 16:48:48,398] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 20 + 0: [2022-11-24 16:48:48,398] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 7 + 2: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:48,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 2: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 16 + 0: [2022-11-24 16:48:48,412] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 5 + 2: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:48,439] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 0 + 2: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 0: checkpoint version 3.0 + 2: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 22 + 0: [2022-11-24 16:48:48,450] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 3 + 2: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 23 + 0: [2022-11-24 16:48:48,461] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 5 + 2: [2022-11-24 16:48:48,370] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:48,475] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 1 + 2: [2022-11-24 16:48:48,371] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 21 + 0: [2022-11-24 16:48:48,509] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 2 + 2: [2022-11-24 16:48:48,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 0: [2022-11-24 16:48:48,691] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 7 + 2: [2022-11-24 16:48:48,373] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 17 + 0: successfully loaded checkpoint from checkpoints_83m at iteration 36000 + 2: [2022-11-24 16:48:48,388] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 19 + 2: [2022-11-24 16:48:48,395] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 16 + 0: estimated model parameters: 0.08274176 + 2: [2022-11-24 16:48:48,406] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 20 + 1: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: estimated model parameters without embeddings: 0.04923648 + 2: [2022-11-24 16:48:48,406] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 18 + 0: [after model, optimizer, and learning rate scheduler are built] datetime: 2022-11-24 16:48:49 + 2: [2022-11-24 16:48:48,435] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 22 + 0: > building train, validation, and test datasets ... + 2: [2022-11-24 16:48:48,441] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 23 + 0: > datasets target sizes (minimum size): + 0: train: 9703701 + 2: [2022-11-24 16:48:48,605] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 21 + 0: validation: 9728 + 0: test: 256 + 2: [2022-11-24 16:48:48,607] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 17 + 0: > building train, validation, and test datasets for GPT ... + 1: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: > building dataset index ... + 1: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: reading sizes... + 0: reading pointers... + 1: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: reading document index... + 0: creating numpy buffer of mmap... + 1: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: creating memory view of numpy buffer... + 1: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: > finished creating indexed dataset in 0.406208 seconds + 1: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: number of documents: 210604984 + 1: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: > dataset split: + 1: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: train: + 1: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: document indices in [0, 199864130) total of 199864130 documents + 1: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: validation: + 0: document indices in [199864130, 210394379) total of 10530249 documents + 1: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: test: + 1: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: document indices in [210394379, 210604984) total of 210605 documents + 1: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:48:48,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:48:48,343] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 10 +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 16:48:48,321] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... + 1: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 11 +16: [2022-11-24 16:48:48,330] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 131 + 1: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,332] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 15 +16: [2022-11-24 16:48:48,332] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 135 + 1: [2022-11-24 16:48:48,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 13 +16: [2022-11-24 16:48:48,337] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 130 + 1: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 14 +16: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 134 + 1: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 128 + 1: [2022-11-24 16:48:48,369] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 12 +16: [2022-11-24 16:48:48,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,369] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 8 +16: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 132 + 1: [2022-11-24 16:48:48,404] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +16: [2022-11-24 16:48:48,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,405] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 9 +16: [2022-11-24 16:48:48,355] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 129 + 1: [2022-11-24 16:48:48,432] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 10 +16: [2022-11-24 16:48:48,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. + 1: [2022-11-24 16:48:48,440] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 13 +16: [2022-11-24 16:48:48,356] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 133 + 1: [2022-11-24 16:48:48,441] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 11 +16: [2022-11-24 16:48:48,461] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 134 + 1: [2022-11-24 16:48:48,441] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 15 +16: [2022-11-24 16:48:48,465] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 129 + 1: [2022-11-24 16:48:48,441] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 8 +16: [2022-11-24 16:48:48,480] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 133 + 1: [2022-11-24 16:48:48,442] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 14 +16: [2022-11-24 16:48:48,496] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 132 + 1: [2022-11-24 16:48:48,446] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 9 +16: [2022-11-24 16:48:48,502] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 135 + 1: [2022-11-24 16:48:48,452] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 12 +16: [2022-11-24 16:48:48,565] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 131 +16: [2022-11-24 16:48:48,566] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 128 +19: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 16:48:48,727] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 130 +19: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,147] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,232] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,338] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 55 +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,338] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 53 +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 52 +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 50 +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 54 +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,361] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 49 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,361] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 51 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 48 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,454] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 53 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,481] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 51 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,481] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 48 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,482] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 54 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 16:48:48,492] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 50 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,493] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 55 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,504] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 52 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 16:48:48,508] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 49 +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,337] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 159 +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,347] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 153 +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,349] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 152 +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,349] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 159 +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 154 +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 16:48:48,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 158 +25: [2022-11-24 16:48:47,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 157 +25: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 156 +25: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,380] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 158 +25: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 16:48:48,415] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +25: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:48,415] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 155 +25: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:48,445] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 156 +25: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:48,477] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 153 +25: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:48,494] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 152 +25: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:48,510] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 154 +25: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 16:48:48,542] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 155 +25: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 16:48:48,552] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 157 +25: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,963] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:47,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,048] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,105] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,226] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 207 + 9: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 206 + 9: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,361] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 201 + 9: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 200 + 9: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 202 + 9: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 204 + 9: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 203 + 9: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,364] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 205 + 9: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 16:48:48,451] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 204 + 9: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 16:48:48,451] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 202 + 9: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 16:48:48,535] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 206 + 9: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,544] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 200 + 9: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 16:48:48,557] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 201 + 9: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 16:48:48,559] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 207 + 9: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 16:48:48,573] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 203 + 9: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 16:48:48,700] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 205 + 9: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,260] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,261] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,262] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,347] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 75 + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 16:48:48,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 74 + 8: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 76 + 8: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 77 + 8: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 72 + 8: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 73 + 8: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 79 + 8: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 8: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,365] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 78 + 8: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,457] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 79 + 8: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,483] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 72 + 8: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,498] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 76 + 8: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,502] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 78 + 8: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,552] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 74 + 8: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 16:48:48,561] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 77 + 8: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,564] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 75 + 8: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 16:48:48,572] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 73 + 8: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,338] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 70 +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,339] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 67 +10: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,339] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 69 +10: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,339] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 71 +10: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,339] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 68 +10: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 66 +10: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,353] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 65 +10: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +10: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 64 +10: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,421] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 64 +10: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,448] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 67 +10: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,461] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 69 +10: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,476] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 65 +10: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,485] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 70 +10: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,498] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 68 +10: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 16:48:48,498] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 71 +10: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 16:48:48,511] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 66 +10: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,259] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 16:48:48,335] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,345] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 85 +11: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,345] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 82 +11: [2022-11-24 16:48:47,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,351] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 84 +11: [2022-11-24 16:48:47,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 86 +11: [2022-11-24 16:48:47,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,371] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 84 +11: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,372] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,373] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,373] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 83 +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,373] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 87 +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,381] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 81 +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,382] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 80 +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,387] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 82 +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,396] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 85 +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,458] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 86 +11: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,563] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 83 +11: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,578] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 87 +11: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 16:48:48,595] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 81 +11: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 16:48:48,596] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 80 +11: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,959] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,962] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,992] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:47,993] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,043] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,044] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,348] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 94 +22: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,348] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 93 +22: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,348] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 91 +22: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,349] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 89 +22: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 90 +22: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 92 +22: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +22: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 88 +22: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 95 +22: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 16:48:48,438] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 91 +22: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,442] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 93 +22: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 16:48:48,461] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 94 +22: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,477] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 88 +22: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 16:48:48,477] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 92 +22: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,480] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 95 +22: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 16:48:48,481] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 89 +22: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 16:48:48,487] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 90 +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 16:48:48,324] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,969] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,345] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 183 +26: [2022-11-24 16:48:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,345] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 179 +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 177 +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 178 +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 180 +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,971] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 182 +26: [2022-11-24 16:48:47,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 16:48:48,352] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,353] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 181 +26: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +26: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,356] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 176 +26: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,456] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 176 +26: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,458] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 182 +26: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,466] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 183 +26: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:48,489] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 181 +26: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:48,501] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 180 +26: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 16:48:48,504] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 177 +26: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:48,545] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 178 +26: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 16:48:48,654] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 179 +26: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 16:48:48,023] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,077] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 16:48:48,077] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,078] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,083] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,116] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 16:48:48,116] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,118] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,122] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,124] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 16:48:48,138] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,140] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:48,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,143] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,143] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:48,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 16:48:48,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,080] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,083] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,147] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:48,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:48,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:48,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,281] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,293] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,293] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 212 +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,293] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 209 +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,293] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 211 +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,303] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 213 +15: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,304] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 16:48:48,304] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 208 +15: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,306] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 214 +15: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,309] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 210 +15: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +15: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,316] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 215 +15: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,372] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 212 +15: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 16:48:48,372] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 208 +15: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,389] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 213 +15: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,399] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 211 +15: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,400] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 209 +15: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,435] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 214 +15: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 16:48:48,519] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 210 +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 16:48:48,590] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 215 +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:47,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:47,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:47,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,322] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,331] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 127 +21: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,340] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 127 +21: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,342] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 125 +21: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,346] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 120 +21: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,351] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 124 +21: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,356] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 122 +21: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 126 +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,376] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 124 +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,382] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,382] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 121 +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,383] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 123 +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,391] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 125 +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,400] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 120 +21: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 16:48:48,416] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 121 +21: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,422] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 123 +21: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,570] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 126 +21: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 16:48:48,638] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 122 +21: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,921] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,957] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,958] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,960] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,961] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:47,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:47,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:47,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:47,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:47,997] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:47,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:47,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:47,998] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,000] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,001] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:48,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 16:48:48,001] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,002] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,002] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,003] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:48,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:48,045] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,046] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:48,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:48,046] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,047] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,048] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,052] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,053] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,055] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,056] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_doc_idx.npy +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_sample_idx.npy +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_shuffle_idx.npy +21: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: loaded indexed file in 0.087 seconds + 0: total number of samples: 173377817 + 0: total number of epochs: 1 +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,331] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 171 +17: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,352] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 175 +17: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 173 +17: [2022-11-24 16:48:48,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,122] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 16:48:48,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 168 +17: [2022-11-24 16:48:48,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 174 +17: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 172 +17: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,365] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 169 +17: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 170 +17: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,403] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 173 +17: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,407] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 171 +17: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,423] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 169 +17: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,426] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 174 +17: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:48,426] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 168 +17: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,426] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 170 +17: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 16:48:48,432] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 172 +17: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 16:48:48,433] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 175 +17: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 16:48:48,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,294] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 142 +28: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,295] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,295] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 141 +28: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,295] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 138 +28: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_doc_idx.npy +17: [2022-11-24 16:48:48,297] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,297] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 136 +28: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 16:48:48,312] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_sample_idx.npy +17: [2022-11-24 16:48:48,312] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 143 +17: [2022-11-24 16:48:48,313] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 16:48:48,314] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 139 +28: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_shuffle_idx.npy +17: [2022-11-24 16:48:48,315] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 16:48:48,315] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 137 +28: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 16:48:48,344] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 142 +28: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 16:48:48,357] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 141 +28: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: loaded indexed file in 0.084 seconds + 0: total number of samples: 9118345 + 0: total number of epochs: 1 +17: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 140 +17: [2022-11-24 16:48:48,374] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 136 +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:48,388] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 138 +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:48,405] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 140 +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 16:48:48,480] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 143 +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 16:48:48,519] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 139 +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 16:48:48,550] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 137 +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy +28: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy +28: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy +28: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: loaded indexed file in 0.052 seconds + 0: total number of samples: 182928 + 0: total number of epochs: 1 +28: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: > finished creating GPT datasets ... +28: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:47,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,136] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,137] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,139] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,141] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,141] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 16:48:48,144] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,146] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,164] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,166] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 16:48:48,167] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +28: [2022-11-24 16:48:48,280] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,296] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,296] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 229 +30: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,303] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 16:48:48,304] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 225 +30: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,308] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 226 +30: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,308] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 230 +30: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,308] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,309] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,309] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 224 +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,309] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 228 +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,311] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 227 +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,311] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +30: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,311] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 231 +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,432] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 224 +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,474] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 229 +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,511] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 225 +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,511] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 230 +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,511] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 228 +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,518] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 227 +30: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 16:48:48,519] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 226 +30: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 16:48:48,520] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 231 +30: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:47,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:47,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [after dataloaders are built] datetime: 2022-11-24 16:49:11 + 0: done with setup ... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: training ... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [000-000] 0.0827B / 0.0492B +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:47,917] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:47,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,389] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 244 +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [before the start of training step] datetime: 2022-11-24 16:49:11 +30: [2022-11-24 16:48:48,389] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 246 +30: [2022-11-24 16:48:48,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,402] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 241 +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,403] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 245 +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,403] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 16:48:48,403] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 240 +18: [2022-11-24 16:48:47,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,412] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,412] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 242 +18: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,413] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:48,413] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 247 +18: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,419] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 246 +18: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,436] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 245 +18: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,439] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +18: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,439] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 243 +18: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:48,451] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 247 +18: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:48,471] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 244 +18: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 16:48:48,472] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 240 +18: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:48,485] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 242 +18: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:48,721] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 243 +18: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 16:48:48,767] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 241 +18: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:47,963] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 16:48:47,965] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,966] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,966] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,968] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:47,969] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,970] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:47,971] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,013] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,013] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,014] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,014] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,015] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,016] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,016] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,018] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,018] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,020] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,021] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,022] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,022] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,049] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,049] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,050] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,050] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,051] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,054] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,054] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,056] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,057] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,057] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,058] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 16:48:48,060] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 16:49:12,159] [INFO] [checkpointing.py:553:forward] Activation Checkpointing Information +18: [2022-11-24 16:48:48,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:49:12,160] [INFO] [checkpointing.py:554:forward] ----Partition Activations False, CPU CHECKPOINTING False +18: [2022-11-24 16:48:48,061] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:49:12,160] [INFO] [checkpointing.py:557:forward] ----contiguous Memory Checkpointing False with None total layers +18: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 16:49:12,160] [INFO] [checkpointing.py:560:forward] ----Synchronization False +18: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 16:49:12,160] [INFO] [checkpointing.py:561:forward] ----Profiling time in checkpointing False +18: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,117] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,119] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,123] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 16:48:48,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,126] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,127] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,127] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 16:48:48,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,130] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,131] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,199] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,199] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,200] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,201] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 16:48:48,207] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,202] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,204] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,205] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,206] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,227] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 16:48:48,279] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,287] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,288] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 144 +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,294] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,294] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 145 +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,300] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,228] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 16:48:48,300] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 148 +29: [2022-11-24 16:48:48,230] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,306] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,306] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 151 +29: [2022-11-24 16:48:48,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,233] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,314] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 149 +29: [2022-11-24 16:48:48,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,314] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 146 +29: [2022-11-24 16:48:48,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,233] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,315] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 147 +29: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +29: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 16:48:48,330] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 150 +29: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:48,363] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 151 +29: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:48,370] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 149 +29: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:48,379] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 146 +29: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:48,381] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 145 +29: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 16:48:48,397] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 147 +29: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:48,460] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 148 +29: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:48,468] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 144 +29: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 16:48:48,600] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 150 +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,305] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,314] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 239 +14: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,316] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,316] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 235 +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,316] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 238 +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,338] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 233 +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,338] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,338] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 237 +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 232 +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,341] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 236 +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,353] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 16:48:48,353] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 234 +14: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,382] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 238 +14: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,409] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 235 +14: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,421] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 232 +14: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,423] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 236 +14: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 16:48:48,423] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 233 +14: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,425] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 237 +14: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,426] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 234 +14: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 16:48:48,429] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 239 +14: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,102] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,103] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,225] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,229] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,341] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 117 + 3: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,343] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 119 + 3: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,343] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 115 + 3: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:48,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 112 + 3: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,350] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:48,350] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 114 + 3: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,350] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 117 + 3: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:48,356] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 16:48:48,357] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 116 + 3: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,357] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 118 + 3: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,386] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 119 + 3: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,387] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 115 + 3: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 16:48:48,389] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 112 + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,390] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 114 + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,399] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 116 + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,405] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 16:48:48,406] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 113 + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:48,430] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 118 + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 16:48:48,439] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 113 + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,257] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,258] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,337] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,337] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 28 +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,337] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 29 +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,340] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 26 +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,357] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,358] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 25 +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,359] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 24 +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 30 +24: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,391] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,392] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 31 +24: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,396] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 29 +24: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,400] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 28 +24: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,402] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. +24: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,402] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 24 +24: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,402] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 30 +24: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,402] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 27 +24: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,403] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 25 +24: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 16:48:48,471] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 26 +24: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,609] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 27 +24: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 16:48:48,615] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 31 +24: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,908] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,944] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,949] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:47,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,972] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,039] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:48,024] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,120] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,121] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,123] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,124] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,125] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,126] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,128] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,317] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,320] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,335] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,089] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,336] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,339] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,340] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,342] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,342] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,344] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,345] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,358] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,359] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,237] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 16:48:48,368] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 16:48:48,435] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,443] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,444] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 196 +13: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,458] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 196 +13: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,467] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,468] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 199 +13: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 16:48:48,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,468] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,469] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 193 +13: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,469] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 194 +13: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,490] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,491] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 198 +13: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,492] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,492] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 192 +13: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,525] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 198 +13: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,526] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 192 +13: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,530] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,530] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 195 +13: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,607] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 199 +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,665] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 194 +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 16:48:48,718] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 197 +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,726] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 195 +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,726] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 193 +13: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 16:48:48,934] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 197 +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:47,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,326] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,345] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,345] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 110 +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,351] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,351] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 106 +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,358] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,358] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 111 +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,359] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 105 +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,359] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 110 +23: [2022-11-24 16:48:47,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,361] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 107 +23: [2022-11-24 16:48:47,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 104 +23: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,369] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,370] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 108 +23: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,380] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 106 +23: [2022-11-24 16:48:47,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,381] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +23: [2022-11-24 16:48:47,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 16:48:48,381] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 109 +23: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:48,400] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 107 +23: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:48,421] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 109 +23: [2022-11-24 16:48:47,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:48,515] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 111 +23: [2022-11-24 16:48:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:48,520] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 104 +23: [2022-11-24 16:48:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:48,521] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 105 +23: [2022-11-24 16:48:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 16:48:48,560] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 108 +23: [2022-11-24 16:48:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:47,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:47,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,903] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,947] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,948] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,950] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 16:48:47,951] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,952] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,953] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,954] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,955] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,956] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,932] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,935] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,988] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,989] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,990] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:47,991] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,033] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,037] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,981] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,040] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,041] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,042] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:47,985] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,028] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,097] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,100] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,101] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,093] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,162] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 16:48:48,163] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,096] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,098] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,099] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,222] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,246] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,161] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,255] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 16:48:48,217] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,220] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,221] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,256] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 186 +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 184 +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,363] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,363] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 191 +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,364] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 189 +20: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,366] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 185 +20: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,366] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 188 +20: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 187 +20: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,367] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +20: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,367] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 190 +20: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 16:48:48,394] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 186 +20: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,408] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 184 +20: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,422] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 187 +20: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,423] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 189 +20: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:48,423] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 191 +20: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,425] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 188 +20: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 16:48:48,434] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 190 +20: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 16:48:48,457] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 185 +20: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:47,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:47,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,330] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 16:48:48,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,341] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,341] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 164 +20: [2022-11-24 16:48:48,341] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 166 +27: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,341] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 161 +27: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 163 +27: [2022-11-24 16:48:47,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,360] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 160 +27: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 165 +27: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,360] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 162 +27: [2022-11-24 16:48:47,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,389] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,389] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 167 +27: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,410] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 161 +27: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,411] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 162 +27: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,411] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 160 +27: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,411] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 163 +27: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,419] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 165 +27: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 16:48:48,447] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 164 +27: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,447] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 167 +27: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 16:48:48,448] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 166 +27: [2022-11-24 16:48:47,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 16:48:47,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 16:48:47,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 16:48:47,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,923] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,924] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,925] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,926] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,927] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 16:48:47,928] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,929] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,930] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,933] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,934] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:47,973] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 16:48:47,936] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,974] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,975] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,937] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,976] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,938] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,939] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,940] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,979] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,941] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,942] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,943] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,945] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,946] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,025] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,977] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,026] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,027] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,978] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,980] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,982] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,031] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:47,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,984] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,986] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:47,987] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,081] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,029] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,030] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 16:48:48,082] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,032] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:48,034] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,087] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,035] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,036] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,038] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,085] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,148] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 16:48:48,086] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,088] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,090] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 16:48:48,091] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,092] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,094] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,154] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,095] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,149] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,150] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,208] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,151] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,152] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,153] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,155] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,156] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,157] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,213] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,158] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,159] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,160] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,210] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,211] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,212] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,214] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,235] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,236] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,215] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 16:48:48,238] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,216] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,239] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,218] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,219] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,240] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,241] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,242] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,243] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,247] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,248] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,249] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,250] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,251] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,252] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,245] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,314] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,328] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 221 +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,328] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,328] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 222 +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,253] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 16:48:48,329] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 217 +31: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,329] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 219 +31: [2022-11-24 16:48:48,254] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 16:48:48,329] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,329] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 218 +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,334] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,334] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 220 +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,333] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +27: [2022-11-24 16:48:48,344] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 223 +31: [2022-11-24 16:48:48,343] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:48,347] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,343] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 248 +27: [2022-11-24 16:48:48,347] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 216 +31: [2022-11-24 16:48:48,355] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:48,395] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 216 +31: [2022-11-24 16:48:48,355] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 252 +27: [2022-11-24 16:48:48,579] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 223 +31: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:48,687] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 222 +31: [2022-11-24 16:48:48,362] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:48,697] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 217 +31: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 249 +27: [2022-11-24 16:48:48,715] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 218 +31: [2022-11-24 16:48:48,362] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 250 +27: [2022-11-24 16:48:48,724] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 220 +31: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:48,744] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 219 +31: [2022-11-24 16:48:48,364] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +27: [2022-11-24 16:48:48,745] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 221 +31: [2022-11-24 16:48:48,364] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 253 +31: [2022-11-24 16:48:48,364] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 251 +31: [2022-11-24 16:48:48,365] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,365] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 254 +31: [2022-11-24 16:48:48,390] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 252 +31: [2022-11-24 16:48:48,395] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 16:48:48,395] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 255 +31: [2022-11-24 16:48:48,396] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 249 +31: [2022-11-24 16:48:48,399] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 250 +31: [2022-11-24 16:48:48,404] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 253 +31: [2022-11-24 16:48:48,404] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 254 +31: [2022-11-24 16:48:48,409] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 251 +31: [2022-11-24 16:48:48,413] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 248 +31: [2022-11-24 16:48:48,611] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 255 +31: time (ms) | load-checkpoint: 1442.18 +31: time (ms) | model-and-optimizer-setup: 30580.61 | train/valid/test-data-iterators-setup: 20680.12 + 0: [Rank 0] (after 36010 iterations) memory (MB) | allocated: 1042.54638671875 | max allocated: 1703.8681640625 | reserved: 2544.0 | max reserved: 2544.0 +31: iteration 36010/ 37905 | consumed samples: 9218560 | consumed tokens: 18879610880 | elapsed time per iteration (s): 1.61 | learning rate: 2.111E-05 | global batch size: 256 | lm loss: 2.875034E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 159.412 | TFLOPs: 1.02 | +31: iteration 36020/ 37905 | consumed samples: 9221120 | consumed tokens: 18884853760 | elapsed time per iteration (s): 0.30 | learning rate: 2.110E-05 | global batch size: 256 | lm loss: 2.886648E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 854.166 | TFLOPs: 5.44 | +31: iteration 36030/ 37905 | consumed samples: 9223680 | consumed tokens: 18890096640 | elapsed time per iteration (s): 0.31 | learning rate: 2.108E-05 | global batch size: 256 | lm loss: 2.865829E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 831.923 | TFLOPs: 5.30 | +31: iteration 36040/ 37905 | consumed samples: 9226240 | consumed tokens: 18895339520 | elapsed time per iteration (s): 0.27 | learning rate: 2.107E-05 | global batch size: 256 | lm loss: 2.881052E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 944.575 | TFLOPs: 6.02 | +31: iteration 36050/ 37905 | consumed samples: 9228800 | consumed tokens: 18900582400 | elapsed time per iteration (s): 0.33 | learning rate: 2.106E-05 | global batch size: 256 | lm loss: 2.905450E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 780.919 | TFLOPs: 4.97 | +31: iteration 36060/ 37905 | consumed samples: 9231360 | consumed tokens: 18905825280 | elapsed time per iteration (s): 0.31 | learning rate: 2.105E-05 | global batch size: 256 | lm loss: 2.913760E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 816.949 | TFLOPs: 5.20 | +31: iteration 36070/ 37905 | consumed samples: 9233920 | consumed tokens: 18911068160 | elapsed time per iteration (s): 0.27 | learning rate: 2.104E-05 | global batch size: 256 | lm loss: 2.899444E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 936.176 | TFLOPs: 5.96 | +31: iteration 36080/ 37905 | consumed samples: 9236480 | consumed tokens: 18916311040 | elapsed time per iteration (s): 0.25 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.876626E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1032.743 | TFLOPs: 6.58 | +31: iteration 36090/ 37905 | consumed samples: 9239040 | consumed tokens: 18921553920 | elapsed time per iteration (s): 0.26 | learning rate: 2.102E-05 | global batch size: 256 | lm loss: 2.869850E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1002.184 | TFLOPs: 6.38 | +31: iteration 36100/ 37905 | consumed samples: 9241600 | consumed tokens: 18926796800 | elapsed time per iteration (s): 0.25 | learning rate: 2.101E-05 | global batch size: 256 | lm loss: 2.925788E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1038.494 | TFLOPs: 6.61 | +31: iteration 36110/ 37905 | consumed samples: 9244160 | consumed tokens: 18932039680 | elapsed time per iteration (s): 0.25 | learning rate: 2.099E-05 | global batch size: 256 | lm loss: 2.901951E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.234 | TFLOPs: 6.55 | +31: iteration 36120/ 37905 | consumed samples: 9246720 | consumed tokens: 18937282560 | elapsed time per iteration (s): 0.29 | learning rate: 2.098E-05 | global batch size: 256 | lm loss: 2.886228E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 879.597 | TFLOPs: 5.60 | +31: iteration 36130/ 37905 | consumed samples: 9249280 | consumed tokens: 18942525440 | elapsed time per iteration (s): 0.28 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 2.864394E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 908.405 | TFLOPs: 5.79 | +31: iteration 36140/ 37905 | consumed samples: 9251840 | consumed tokens: 18947768320 | elapsed time per iteration (s): 0.29 | learning rate: 2.096E-05 | global batch size: 256 | lm loss: 2.870307E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 890.735 | TFLOPs: 5.67 | +31: iteration 36150/ 37905 | consumed samples: 9254400 | consumed tokens: 18953011200 | elapsed time per iteration (s): 0.26 | learning rate: 2.095E-05 | global batch size: 256 | lm loss: 2.926268E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 982.002 | TFLOPs: 6.25 | +31: iteration 36160/ 37905 | consumed samples: 9256960 | consumed tokens: 18958254080 | elapsed time per iteration (s): 0.27 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 2.925979E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 941.834 | TFLOPs: 6.00 | +31: iteration 36170/ 37905 | consumed samples: 9259520 | consumed tokens: 18963496960 | elapsed time per iteration (s): 0.24 | learning rate: 2.093E-05 | global batch size: 256 | lm loss: 2.908002E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.824 | TFLOPs: 6.66 | +31: iteration 36180/ 37905 | consumed samples: 9262080 | consumed tokens: 18968739840 | elapsed time per iteration (s): 0.21 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.891486E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1206.252 | TFLOPs: 7.68 | +31: iteration 36190/ 37905 | consumed samples: 9264640 | consumed tokens: 18973982720 | elapsed time per iteration (s): 0.21 | learning rate: 2.091E-05 | global batch size: 256 | lm loss: 2.885267E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.780 | TFLOPs: 7.93 | +31: iteration 36200/ 37905 | consumed samples: 9267200 | consumed tokens: 18979225600 | elapsed time per iteration (s): 0.23 | learning rate: 2.090E-05 | global batch size: 256 | lm loss: 2.914770E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.696 | TFLOPs: 6.97 | +31: iteration 36210/ 37905 | consumed samples: 9269760 | consumed tokens: 18984468480 | elapsed time per iteration (s): 0.21 | learning rate: 2.089E-05 | global batch size: 256 | lm loss: 2.879210E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1248.053 | TFLOPs: 7.95 | +31: iteration 36220/ 37905 | consumed samples: 9272320 | consumed tokens: 18989711360 | elapsed time per iteration (s): 0.21 | learning rate: 2.088E-05 | global batch size: 256 | lm loss: 2.916792E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1198.038 | TFLOPs: 7.63 | +31: iteration 36230/ 37905 | consumed samples: 9274880 | consumed tokens: 18994954240 | elapsed time per iteration (s): 0.25 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 2.907865E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1003.972 | TFLOPs: 6.39 | +31: iteration 36240/ 37905 | consumed samples: 9277440 | consumed tokens: 19000197120 | elapsed time per iteration (s): 0.25 | learning rate: 2.086E-05 | global batch size: 256 | lm loss: 2.906250E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.044 | TFLOPs: 6.45 | +31: iteration 36250/ 37905 | consumed samples: 9280000 | consumed tokens: 19005440000 | elapsed time per iteration (s): 0.22 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 2.873895E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1144.042 | TFLOPs: 7.29 | +31: iteration 36260/ 37905 | consumed samples: 9282560 | consumed tokens: 19010682880 | elapsed time per iteration (s): 0.21 | learning rate: 2.084E-05 | global batch size: 256 | lm loss: 2.863333E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1202.922 | TFLOPs: 7.66 | +31: iteration 36270/ 37905 | consumed samples: 9285120 | consumed tokens: 19015925760 | elapsed time per iteration (s): 0.22 | learning rate: 2.083E-05 | global batch size: 256 | lm loss: 2.908844E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1173.207 | TFLOPs: 7.47 | +31: iteration 36280/ 37905 | consumed samples: 9287680 | consumed tokens: 19021168640 | elapsed time per iteration (s): 0.23 | learning rate: 2.082E-05 | global batch size: 256 | lm loss: 2.878504E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.705 | TFLOPs: 7.21 | +31: iteration 36290/ 37905 | consumed samples: 9290240 | consumed tokens: 19026411520 | elapsed time per iteration (s): 0.22 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.909422E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.396 | TFLOPs: 7.45 | +31: iteration 36300/ 37905 | consumed samples: 9292800 | consumed tokens: 19031654400 | elapsed time per iteration (s): 0.22 | learning rate: 2.080E-05 | global batch size: 256 | lm loss: 2.912795E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.030 | TFLOPs: 7.30 | +31: iteration 36310/ 37905 | consumed samples: 9295360 | consumed tokens: 19036897280 | elapsed time per iteration (s): 0.23 | learning rate: 2.079E-05 | global batch size: 256 | lm loss: 2.908192E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.732 | TFLOPs: 7.14 | +31: iteration 36320/ 37905 | consumed samples: 9297920 | consumed tokens: 19042140160 | elapsed time per iteration (s): 0.26 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 2.877349E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 990.005 | TFLOPs: 6.31 | +31: iteration 36330/ 37905 | consumed samples: 9300480 | consumed tokens: 19047383040 | elapsed time per iteration (s): 0.24 | learning rate: 2.077E-05 | global batch size: 256 | lm loss: 2.855331E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.031 | TFLOPs: 6.80 | +31: iteration 36340/ 37905 | consumed samples: 9303040 | consumed tokens: 19052625920 | elapsed time per iteration (s): 0.27 | learning rate: 2.076E-05 | global batch size: 256 | lm loss: 2.895671E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 963.504 | TFLOPs: 6.14 | +31: iteration 36350/ 37905 | consumed samples: 9305600 | consumed tokens: 19057868800 | elapsed time per iteration (s): 0.25 | learning rate: 2.075E-05 | global batch size: 256 | lm loss: 2.861573E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1039.004 | TFLOPs: 6.62 | +31: iteration 36360/ 37905 | consumed samples: 9308160 | consumed tokens: 19063111680 | elapsed time per iteration (s): 0.24 | learning rate: 2.074E-05 | global batch size: 256 | lm loss: 2.903195E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.526 | TFLOPs: 6.84 | +31: iteration 36370/ 37905 | consumed samples: 9310720 | consumed tokens: 19068354560 | elapsed time per iteration (s): 0.27 | learning rate: 2.073E-05 | global batch size: 256 | lm loss: 2.890572E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 944.116 | TFLOPs: 6.01 | +31: iteration 36380/ 37905 | consumed samples: 9313280 | consumed tokens: 19073597440 | elapsed time per iteration (s): 0.24 | learning rate: 2.072E-05 | global batch size: 256 | lm loss: 2.911003E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1078.932 | TFLOPs: 6.87 | +31: iteration 36390/ 37905 | consumed samples: 9315840 | consumed tokens: 19078840320 | elapsed time per iteration (s): 0.25 | learning rate: 2.071E-05 | global batch size: 256 | lm loss: 2.882359E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1022.371 | TFLOPs: 6.51 | +31: iteration 36400/ 37905 | consumed samples: 9318400 | consumed tokens: 19084083200 | elapsed time per iteration (s): 0.25 | learning rate: 2.070E-05 | global batch size: 256 | lm loss: 2.912443E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1013.520 | TFLOPs: 6.45 | +31: iteration 36410/ 37905 | consumed samples: 9320960 | consumed tokens: 19089326080 | elapsed time per iteration (s): 0.25 | learning rate: 2.069E-05 | global batch size: 256 | lm loss: 2.871431E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1035.474 | TFLOPs: 6.59 | +31: iteration 36420/ 37905 | consumed samples: 9323520 | consumed tokens: 19094568960 | elapsed time per iteration (s): 0.23 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 2.874770E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1104.297 | TFLOPs: 7.03 | +31: iteration 36430/ 37905 | consumed samples: 9326080 | consumed tokens: 19099811840 | elapsed time per iteration (s): 0.28 | learning rate: 2.067E-05 | global batch size: 256 | lm loss: 2.890210E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 901.694 | TFLOPs: 5.74 | +31: iteration 36440/ 37905 | consumed samples: 9328640 | consumed tokens: 19105054720 | elapsed time per iteration (s): 0.26 | learning rate: 2.066E-05 | global batch size: 256 | lm loss: 2.869658E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.883 | TFLOPs: 6.35 | +31: iteration 36450/ 37905 | consumed samples: 9331200 | consumed tokens: 19110297600 | elapsed time per iteration (s): 0.25 | learning rate: 2.065E-05 | global batch size: 256 | lm loss: 2.908603E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.916 | TFLOPs: 6.56 | +31: iteration 36460/ 37905 | consumed samples: 9333760 | consumed tokens: 19115540480 | elapsed time per iteration (s): 0.32 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 2.884865E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 809.432 | TFLOPs: 5.16 | +31: iteration 36470/ 37905 | consumed samples: 9336320 | consumed tokens: 19120783360 | elapsed time per iteration (s): 0.27 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 2.872897E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 965.738 | TFLOPs: 6.15 | +31: iteration 36480/ 37905 | consumed samples: 9338880 | consumed tokens: 19126026240 | elapsed time per iteration (s): 0.28 | learning rate: 2.063E-05 | global batch size: 256 | lm loss: 2.898441E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 914.744 | TFLOPs: 5.83 | +31: iteration 36490/ 37905 | consumed samples: 9341440 | consumed tokens: 19131269120 | elapsed time per iteration (s): 0.24 | learning rate: 2.062E-05 | global batch size: 256 | lm loss: 2.908790E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1072.765 | TFLOPs: 6.83 | +31: iteration 36500/ 37905 | consumed samples: 9344000 | consumed tokens: 19136512000 | elapsed time per iteration (s): 0.24 | learning rate: 2.061E-05 | global batch size: 256 | lm loss: 2.859162E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.600 | TFLOPs: 6.75 | +31: iteration 36510/ 37905 | consumed samples: 9346560 | consumed tokens: 19141754880 | elapsed time per iteration (s): 0.26 | learning rate: 2.060E-05 | global batch size: 256 | lm loss: 2.901369E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 990.454 | TFLOPs: 6.31 | +31: iteration 36520/ 37905 | consumed samples: 9349120 | consumed tokens: 19146997760 | elapsed time per iteration (s): 0.23 | learning rate: 2.059E-05 | global batch size: 256 | lm loss: 2.859150E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.583 | TFLOPs: 7.09 | +31: iteration 36530/ 37905 | consumed samples: 9351680 | consumed tokens: 19152240640 | elapsed time per iteration (s): 0.27 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.892040E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 931.159 | TFLOPs: 5.93 | +31: iteration 36540/ 37905 | consumed samples: 9354240 | consumed tokens: 19157483520 | elapsed time per iteration (s): 0.25 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.892833E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.372 | TFLOPs: 6.50 | +31: iteration 36550/ 37905 | consumed samples: 9356800 | consumed tokens: 19162726400 | elapsed time per iteration (s): 0.23 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 2.890966E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1116.574 | TFLOPs: 7.11 | +31: iteration 36560/ 37905 | consumed samples: 9359360 | consumed tokens: 19167969280 | elapsed time per iteration (s): 0.24 | learning rate: 2.056E-05 | global batch size: 256 | lm loss: 2.902261E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.403 | TFLOPs: 6.91 | +31: iteration 36570/ 37905 | consumed samples: 9361920 | consumed tokens: 19173212160 | elapsed time per iteration (s): 0.24 | learning rate: 2.055E-05 | global batch size: 256 | lm loss: 2.873650E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1045.243 | TFLOPs: 6.66 | +31: iteration 36580/ 37905 | consumed samples: 9364480 | consumed tokens: 19178455040 | elapsed time per iteration (s): 0.23 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.861152E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1105.778 | TFLOPs: 7.04 | +31: iteration 36590/ 37905 | consumed samples: 9367040 | consumed tokens: 19183697920 | elapsed time per iteration (s): 0.22 | learning rate: 2.053E-05 | global batch size: 256 | lm loss: 2.879736E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1165.230 | TFLOPs: 7.42 | +31: iteration 36600/ 37905 | consumed samples: 9369600 | consumed tokens: 19188940800 | elapsed time per iteration (s): 0.26 | learning rate: 2.053E-05 | global batch size: 256 | lm loss: 2.841673E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 999.871 | TFLOPs: 6.37 | +31: iteration 36610/ 37905 | consumed samples: 9372160 | consumed tokens: 19194183680 | elapsed time per iteration (s): 0.25 | learning rate: 2.052E-05 | global batch size: 256 | lm loss: 2.921107E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1013.586 | TFLOPs: 6.46 | +31: iteration 36620/ 37905 | consumed samples: 9374720 | consumed tokens: 19199426560 | elapsed time per iteration (s): 0.23 | learning rate: 2.051E-05 | global batch size: 256 | lm loss: 2.891282E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1109.348 | TFLOPs: 7.07 | +31: iteration 36630/ 37905 | consumed samples: 9377280 | consumed tokens: 19204669440 | elapsed time per iteration (s): 0.24 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.837898E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1082.420 | TFLOPs: 6.89 | +31: iteration 36640/ 37905 | consumed samples: 9379840 | consumed tokens: 19209912320 | elapsed time per iteration (s): 0.23 | learning rate: 2.049E-05 | global batch size: 256 | lm loss: 2.883154E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.045 | TFLOPs: 6.97 | +31: iteration 36650/ 37905 | consumed samples: 9382400 | consumed tokens: 19215155200 | elapsed time per iteration (s): 0.25 | learning rate: 2.049E-05 | global batch size: 256 | lm loss: 2.869710E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1030.292 | TFLOPs: 6.56 | +31: iteration 36660/ 37905 | consumed samples: 9384960 | consumed tokens: 19220398080 | elapsed time per iteration (s): 0.26 | learning rate: 2.048E-05 | global batch size: 256 | lm loss: 2.890990E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 988.640 | TFLOPs: 6.30 | +31: iteration 36670/ 37905 | consumed samples: 9387520 | consumed tokens: 19225640960 | elapsed time per iteration (s): 0.24 | learning rate: 2.047E-05 | global batch size: 256 | lm loss: 2.905231E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1080.889 | TFLOPs: 6.88 | +31: iteration 36680/ 37905 | consumed samples: 9390080 | consumed tokens: 19230883840 | elapsed time per iteration (s): 0.26 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.890004E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 971.351 | TFLOPs: 6.19 | +31: iteration 36690/ 37905 | consumed samples: 9392640 | consumed tokens: 19236126720 | elapsed time per iteration (s): 0.25 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.886239E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1036.348 | TFLOPs: 6.60 | +31: iteration 36700/ 37905 | consumed samples: 9395200 | consumed tokens: 19241369600 | elapsed time per iteration (s): 0.23 | learning rate: 2.045E-05 | global batch size: 256 | lm loss: 2.884292E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.173 | TFLOPs: 7.14 | +31: iteration 36710/ 37905 | consumed samples: 9397760 | consumed tokens: 19246612480 | elapsed time per iteration (s): 0.24 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 2.872428E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.399 | TFLOPs: 6.68 | +31: iteration 36720/ 37905 | consumed samples: 9400320 | consumed tokens: 19251855360 | elapsed time per iteration (s): 0.23 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 2.869320E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1125.764 | TFLOPs: 7.17 | +31: iteration 36730/ 37905 | consumed samples: 9402880 | consumed tokens: 19257098240 | elapsed time per iteration (s): 0.23 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 2.892738E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.243 | TFLOPs: 7.07 | +31: iteration 36740/ 37905 | consumed samples: 9405440 | consumed tokens: 19262341120 | elapsed time per iteration (s): 0.22 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.901523E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.306 | TFLOPs: 7.31 | +31: iteration 36750/ 37905 | consumed samples: 9408000 | consumed tokens: 19267584000 | elapsed time per iteration (s): 0.22 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 2.876865E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1153.903 | TFLOPs: 7.35 | +31: iteration 36760/ 37905 | consumed samples: 9410560 | consumed tokens: 19272826880 | elapsed time per iteration (s): 0.22 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 2.895394E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1148.247 | TFLOPs: 7.31 | +31: iteration 36770/ 37905 | consumed samples: 9413120 | consumed tokens: 19278069760 | elapsed time per iteration (s): 0.24 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 2.878531E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.867 | TFLOPs: 6.81 | +31: iteration 36780/ 37905 | consumed samples: 9415680 | consumed tokens: 19283312640 | elapsed time per iteration (s): 0.25 | learning rate: 2.039E-05 | global batch size: 256 | lm loss: 2.917804E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.818 | TFLOPs: 6.49 | +31: iteration 36790/ 37905 | consumed samples: 9418240 | consumed tokens: 19288555520 | elapsed time per iteration (s): 0.25 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.904743E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.078 | TFLOPs: 6.50 | +31: iteration 36800/ 37905 | consumed samples: 9420800 | consumed tokens: 19293798400 | elapsed time per iteration (s): 0.24 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.870599E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1051.867 | TFLOPs: 6.70 | +31: iteration 36810/ 37905 | consumed samples: 9423360 | consumed tokens: 19299041280 | elapsed time per iteration (s): 0.27 | learning rate: 2.037E-05 | global batch size: 256 | lm loss: 2.895813E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 954.421 | TFLOPs: 6.08 | +31: iteration 36820/ 37905 | consumed samples: 9425920 | consumed tokens: 19304284160 | elapsed time per iteration (s): 0.26 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.901664E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.885 | TFLOPs: 6.33 | +31: iteration 36830/ 37905 | consumed samples: 9428480 | consumed tokens: 19309527040 | elapsed time per iteration (s): 0.22 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.899883E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1171.277 | TFLOPs: 7.46 | +31: iteration 36840/ 37905 | consumed samples: 9431040 | consumed tokens: 19314769920 | elapsed time per iteration (s): 0.23 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 2.873335E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1097.688 | TFLOPs: 6.99 | +31: iteration 36850/ 37905 | consumed samples: 9433600 | consumed tokens: 19320012800 | elapsed time per iteration (s): 0.24 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.909697E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1063.966 | TFLOPs: 6.78 | +31: iteration 36860/ 37905 | consumed samples: 9436160 | consumed tokens: 19325255680 | elapsed time per iteration (s): 0.21 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.896464E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1190.869 | TFLOPs: 7.58 | +31: iteration 36870/ 37905 | consumed samples: 9438720 | consumed tokens: 19330498560 | elapsed time per iteration (s): 0.27 | learning rate: 2.033E-05 | global batch size: 256 | lm loss: 2.861786E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 959.130 | TFLOPs: 6.11 | +31: iteration 36880/ 37905 | consumed samples: 9441280 | consumed tokens: 19335741440 | elapsed time per iteration (s): 0.25 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.854629E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.520 | TFLOPs: 6.59 | +31: 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: 2.875157E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1119.291 | TFLOPs: 7.13 | +31: iteration 36900/ 37905 | consumed samples: 9446400 | consumed tokens: 19346227200 | elapsed time per iteration (s): 0.23 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.921170E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1124.864 | TFLOPs: 7.16 | +31: iteration 36910/ 37905 | consumed samples: 9448960 | consumed tokens: 19351470080 | elapsed time per iteration (s): 0.26 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.924317E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 969.081 | TFLOPs: 6.17 | +31: iteration 36920/ 37905 | consumed samples: 9451520 | consumed tokens: 19356712960 | elapsed time per iteration (s): 0.23 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 2.893167E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1130.938 | TFLOPs: 7.20 | +31: iteration 36930/ 37905 | consumed samples: 9454080 | consumed tokens: 19361955840 | elapsed time per iteration (s): 0.26 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.908124E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 967.755 | TFLOPs: 6.16 | +31: iteration 36940/ 37905 | consumed samples: 9456640 | consumed tokens: 19367198720 | elapsed time per iteration (s): 0.25 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.926399E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.160 | TFLOPs: 6.58 | +31: iteration 36950/ 37905 | consumed samples: 9459200 | consumed tokens: 19372441600 | elapsed time per iteration (s): 0.25 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.885104E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1014.637 | TFLOPs: 6.46 | +31: iteration 36960/ 37905 | consumed samples: 9461760 | consumed tokens: 19377684480 | elapsed time per iteration (s): 0.22 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.866648E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1178.484 | TFLOPs: 7.51 | +31: iteration 36970/ 37905 | consumed samples: 9464320 | consumed tokens: 19382927360 | elapsed time per iteration (s): 0.28 | learning rate: 2.027E-05 | global batch size: 256 | lm loss: 2.908297E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 908.678 | TFLOPs: 5.79 | +31: iteration 36980/ 37905 | consumed samples: 9466880 | consumed tokens: 19388170240 | elapsed time per iteration (s): 0.24 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.902516E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1070.869 | TFLOPs: 6.82 | +31: iteration 36990/ 37905 | consumed samples: 9469440 | consumed tokens: 19393413120 | elapsed time per iteration (s): 0.27 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.872168E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 934.016 | TFLOPs: 5.95 | +31: iteration 37000/ 37905 | consumed samples: 9472000 | consumed tokens: 19398656000 | elapsed time per iteration (s): 0.24 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 2.880073E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1049.924 | TFLOPs: 6.69 | diff --git a/logs/2058110_120.err b/logs/2058110_120.err new file mode 100644 index 0000000000000000000000000000000000000000..29fd3b83b0826c84f13381df04497a96d13e1530 --- /dev/null +++ b/logs/2058110_120.err @@ -0,0 +1,1844 @@ +23: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +23: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +23: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +19: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': 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 +21: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +21: rm: cannot remove '/dev/shm/hsakmt_shared_mem': Operation not permitted +21: rm: cannot remove '/dev/shm/sem.hsakmt_semaphore': Operation not permitted +20: rm: cannot remove '/dev/shm/gtl-shared-mem-setup-kvs_2051275.0-327000036.tmp': Operation not permitted +20: rm: cannot remove '/dev/shm/hsakmt_shared_mem': 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. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 0: Successfully preprocessed all matching files. + 4: Successfully preprocessed all matching files. + 4: Successfully preprocessed all matching files. + 4: Successfully preprocessed all matching files. + 3: Successfully preprocessed all matching files. +31: Successfully preprocessed all matching files. +26: Successfully preprocessed all matching files. +18: Successfully preprocessed all matching files. + 5: Successfully preprocessed all matching files. +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( +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( + 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( +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( +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( + 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( + 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( +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( +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( +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( +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( + 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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( + 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( +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( +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( + 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( +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( +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( + 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( +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( +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( +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( +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( +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( + 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( +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( + 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( + 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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( + 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( +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( + 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( +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( +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( + 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( +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( +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( + 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( +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( + 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( + 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( +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( +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( +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( +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( +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( +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( + 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( + 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( + 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( + 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( +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( +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( +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( + 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( +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( + 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( + 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( + 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( +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( + 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( +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( +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( + 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( +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( +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( +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( +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( + 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( + 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( +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( + 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( + 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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( + 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( + 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( +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( + 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( +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( +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( +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( + 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( +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( +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( +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( +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( + 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( + 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( +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( + 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( +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( +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( + 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( +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( + 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( + 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( + 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( +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( + 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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( +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( + 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( +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( +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( + 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( +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( +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( +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( +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( +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( + 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( +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( +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( +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( + 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( + 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( +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( + 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( +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( + 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( +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( + 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... + 7: 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... +13: 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... +22: 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... +29: 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: Using /pfs/lustrep4/users/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... + 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... + 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... + 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... + 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... + 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... + 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... + 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... + 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... + 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... + 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... + 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...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... + 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...Using /pfs/lustrep4/users/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: 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... + 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: + 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: + 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... + 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... + 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: + 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... +10: 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... +10: 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... +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... +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... +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... +11: 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... +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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: +11: 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... +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... +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... +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: Using /pfs/lustrep4/users/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... +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... +11: 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... +11: 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... +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... +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... +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... +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... +15: +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... +15: +15: 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... +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... +16: +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... +16: +16: 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: +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... +18: 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... +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: +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: 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... +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... +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... +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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +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: 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: 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: 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: 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: 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... +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... +22: 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... +22: 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... +23: 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... +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... +24: 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... +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... +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... +24: 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: 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... +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... +25: 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... +26: 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... +25: 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... +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... +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: +28: 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... +28: 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... +28: 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... +28: 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... +29: 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... +29: 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... +29: 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... +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... +30: +30: 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... +30: 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... +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... +30: +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... + 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) + 7: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 1: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 6: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 6: Loading extension module utils... + 8: Loading extension module utils... +13: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 8: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... + 9: Loading extension module utils... +11: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +10: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +11: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +12: Loading extension module utils... +12: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +13: Loading extension module utils... +11: Loading extension module utils... +14: Loading extension module utils... +11: Loading extension module utils... +14: Loading extension module utils... +11: Loading extension module utils... +14: Loading extension module utils... +14: Loading extension module utils... +11: Loading extension module utils... +14: Loading extension module utils... +11: Loading extension module utils... +14: Loading extension module utils... +11: Loading extension module utils... +14: Loading extension module utils... +14: 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... +15: Loading extension module utils... +22: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +16: Loading extension module utils... +18: Loading extension module utils... +17: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +17: Loading extension module utils... +18: Loading extension module utils... +17: Loading extension module utils... +18: Loading extension module utils... +18: Loading extension module utils... +17: Loading extension module utils... +17: Loading extension module utils... +19: Loading extension module utils... +17: Loading extension module utils... +19: Loading extension module utils... +17: Loading extension module utils... +20: Loading extension module utils... +17: Loading extension module utils... +19: Loading extension module utils... +26: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +20: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +19: Loading extension module utils... +19: Loading extension module utils... +20: Loading extension module utils... +20: 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... +21: Loading extension module utils... +22: Loading extension module utils... +21: Loading extension module utils... +29: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +21: Loading extension module utils... +23: Loading extension module utils... +22: Loading extension module utils... +21: Loading extension module utils... +22: Loading extension module utils... +23: Loading extension module utils... +24: Loading extension module utils... +22: 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... +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... +23: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +26: Loading extension module utils... +25: Loading extension module utils... +25: Loading extension module utils... +26: Loading extension module utils... +25: Loading extension module utils... +26: 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... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +27: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +29: Loading extension module utils... +28: Loading extension module utils... +28: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +31: Loading extension module utils... +30: Loading extension module utils... + 0: Loading extension module utils... +30: Loading extension module utils... +31: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +30: Loading extension module utils... +31: 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... + 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... + 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... + 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... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: Loading extension module utils... + 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... + 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... + 6: No modifications detected for re-loaded extension module utils, skipping build step... + 6: 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: 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... + 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: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 8: No modifications detected for re-loaded extension module utils, skipping build step... + 8: 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: 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: Loading extension module utils...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: No modifications detected for re-loaded extension module utils, skipping build step... + 8: 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... + 8: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... + 8: + 8: Loading extension module utils...Loading extension module utils... + 8: + 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... + 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: No modifications detected for re-loaded extension module utils, skipping build step... + 9: Loading extension module utils... + 9: 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: 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... + 9: Loading extension module utils... + 9: 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: 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: 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... +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... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: 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... +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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: 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... +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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +10: No modifications detected for re-loaded extension module utils, skipping build step... +10: Loading extension module utils... +13: 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: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: 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: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +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... +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: +12: Loading extension module utils...Loading extension module utils... +12: +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +12: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +12: No modifications detected for re-loaded extension module utils, skipping build step... +12: Loading extension module utils... +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: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +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: 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... +13: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +13: No modifications detected for re-loaded extension module utils, skipping build step... +13: Loading extension module utils... +11: 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: 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: No modifications detected for re-loaded extension module utils, skipping build step... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +13: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +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... +11: 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... +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... +13: Loading extension module utils... +11: 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... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +14: +14: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: Loading extension module utils... +14: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: No modifications detected for re-loaded extension module utils, skipping build step... +14: 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... +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... +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... +11: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +14: Loading extension module utils... +11: No modifications detected for re-loaded extension module utils, skipping build step... +11: Loading extension module utils... +15: 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... +15: 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... +15: 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... +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... +16: 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... +15: 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...Loading extension module utils... +15: +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +15: No modifications detected for re-loaded extension module utils, skipping build step... +15: Loading extension module utils... +16: 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... +16: 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... +16: 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +16: +16: Loading extension module utils... +16: No modifications detected for re-loaded extension module utils, skipping build step... +16: Loading extension module utils... +17: 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... +16: 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: 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: 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... +15: 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... +15: 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... +17: 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... +17: 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... +17: No modifications detected for re-loaded extension module utils, skipping build step... +17: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Loading extension module utils... +17: +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: 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: 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... +20: 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... +20: No modifications detected for re-loaded extension module utils, skipping build step... +20: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +19: 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... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +19: 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... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +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... +19: Loading extension module utils... +18: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +18: 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... +22: 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... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: Loading extension module utils... +19: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +18: No modifications detected for re-loaded extension module utils, skipping build step... +18: 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... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: Loading extension module utils... +20: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +19: 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... +19: No modifications detected for re-loaded extension module utils, skipping build step... +19: 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: 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...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +20: +20: Loading extension module utils... +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: 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... +21: 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: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: 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: 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...No modifications detected for re-loaded extension module utils, skipping build step... +21: +21: Loading extension module utils...Loading extension module utils... +21: +21: No modifications detected for re-loaded extension module utils, skipping build step... +21: Loading extension module utils... +21: 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... +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... +22: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +22: No modifications detected for re-loaded extension module utils, skipping build step... +22: Loading extension module utils... +21: 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... +21: 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... +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... +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... +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... +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... +23: 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... +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... +23: +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: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +26: 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...No modifications detected for re-loaded extension module utils, skipping build step... +23: +23: Loading extension module utils...Loading extension module utils... +23: +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +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... +23: 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... +23: No modifications detected for re-loaded extension module utils, skipping build step... +23: Loading extension module utils... +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... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +24: +24: Loading extension module utils... +24: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +25: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +24: 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: 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... +25: Loading extension module utils... +24: No modifications detected for re-loaded extension module utils, skipping build step... +24: Loading extension module utils... +25: 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... +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... +25: 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... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +25: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: 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... +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... +26: Loading extension module utils... +25: 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... +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: +26: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +25: No modifications detected for re-loaded extension module utils, skipping build step... +25: Loading extension module utils... +26: No modifications detected for re-loaded extension module utils, skipping build step... +26: Loading extension module utils... +25: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +25: +25: Loading extension module utils...Loading extension module utils... +25: +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... +26: Loading extension module utils... +26: 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... +27: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +29: 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: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +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... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +27: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +28: 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: No modifications detected for re-loaded extension module utils, skipping build step... +27: Loading extension module utils... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: 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: No modifications detected for re-loaded extension module utils, skipping build step... +27: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +27: +27: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +28: 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...No modifications detected for re-loaded extension module utils, skipping build step... +28: +28: Loading extension module utils... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +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... +28: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +29: 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... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +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: Loading extension module utils... +28: 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... +28: No modifications detected for re-loaded extension module utils, skipping build step... +28: Loading extension module utils... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: 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... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +29: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +29: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +29: +29: Loading extension module utils...Loading extension module utils... +29: +29: No modifications detected for re-loaded extension module utils, skipping build step... +29: Loading extension module utils... +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: 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... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +30: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +31: 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... +30: No modifications detected for re-loaded extension module utils, skipping build step...Using /pfs/lustrep4/users/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: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... + 1: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +31: Loading extension module utils... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +30: No modifications detected for re-loaded extension module utils, skipping build step... +30: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 1: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 1: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... + 1: + 1: + 1: +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: No modifications detected for re-loaded extension module utils, skipping build step... + 0: Loading extension module utils... +31: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 0: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 0: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 0: Loading extension module utils... +31: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: Loading extension module utils... + 0: Loading extension module utils... +31: No modifications detected for re-loaded extension module utils, skipping build step... +31: 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... + 2: Loading extension module utils... + 7: Loading extension module utils... + 4: 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... + 3: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... + 4: Loading extension module utils... + 3: Loading extension module utils... + 3: Loading extension module utils... + 4: Loading extension module utils... + 4: Loading extension module utils... + 9: 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...Loading extension module utils... + 7: + 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... + 7: Loading extension module utils...Loading extension module utils... + 7: + 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: 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: Using /pfs/lustrep4/users/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: 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...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... + 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: + 0: Loading extension module utils...Loading extension module utils...Loading extension module utils... + 0: + 0: + 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... + 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: 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: 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: 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: 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... + 2: No modifications detected for re-loaded extension module utils, skipping build step... + 2: Loading extension module utils... + 9: 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... + 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...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: + 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Loading extension module utils... + 3: + 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... + 4: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... + 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... + 4: 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: 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: 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: 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: 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...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... + 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: 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: + 7: 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... + 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: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... + 5: + 5: Loading extension module utils... + 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... + 7: No modifications detected for re-loaded extension module utils, skipping build step... + 7: Loading extension module utils... + 5: 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... + 5: Loading extension module utils... + 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... + 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... + 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/logs/2058110_120.out b/logs/2058110_120.out new file mode 100644 index 0000000000000000000000000000000000000000..f6d93a130c251f8f6ade9817e338d1c17cc6c01f --- /dev/null +++ b/logs/2058110_120.out @@ -0,0 +1,18377 @@ + 0: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 5: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +12: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 0: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 5: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 0: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 0: START 2058110: Thu Nov 24 17:04:50 EET 2022 + 5: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 5: START 2058110: Thu Nov 24 17:04:50 EET 2022 +12: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +12: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +12: START 2058110: Thu Nov 24 17:04:50 EET 2022 +11: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 6: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +23: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +26: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 3: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +14: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +19: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +15: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +11: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +11: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +11: START 2058110: Thu Nov 24 17:04:50 EET 2022 + 7: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +29: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +31: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 2: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +22: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +24: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +10: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 4: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 8: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +16: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +25: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +30: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 9: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +17: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +28: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +27: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +21: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +18: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +13: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 1: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 +23: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +23: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +23: START 2058110: Thu Nov 24 17:04:50 EET 2022 + 6: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 6: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 6: START 2058110: Thu Nov 24 17:04:50 EET 2022 +20: Model parameters: d_model 640 ffw_size 2560 kv_size 64 n_heads 10 n_layers 10 + 3: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 3: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 3: START 2058110: Thu Nov 24 17:04:50 EET 2022 +14: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +14: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +14: START 2058110: Thu Nov 24 17:04:50 EET 2022 +19: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +19: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +19: START 2058110: Thu Nov 24 17:04:50 EET 2022 +26: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +26: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +26: START 2058110: Thu Nov 24 17:04:50 EET 2022 +15: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +15: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +15: START 2058110: Thu Nov 24 17:04:50 EET 2022 + 7: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 7: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 7: START 2058110: Thu Nov 24 17:04:50 EET 2022 +24: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +24: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +24: START 2058110: Thu Nov 24 17:04:50 EET 2022 +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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +10: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +16: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +10: START 2058110: Thu Nov 24 17:04:50 EET 2022 +16: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +16: START 2058110: Thu Nov 24 17:04:50 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 41.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 2 38.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 4 36.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 0: 6 36.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 0: 7 48.0c 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 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 2 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 4 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: 6 42.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 5: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 5: ================================================================================ + 5: ============================= 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 45.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 1 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 2 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 4 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: 6 45.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +12: 7 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +12: ================================================================================ +12: ============================= 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 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 2 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 4 45.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: 6 37.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +11: 7 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +11: ================================================================================ +11: ============================= End of ROCm SMI Log ============================== + 4: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 4: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 4: START 2058110: Thu Nov 24 17:04:51 EET 2022 +25: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +25: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +25: START 2058110: Thu Nov 24 17:04:51 EET 2022 +29: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +29: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +29: START 2058110: Thu Nov 24 17:04:51 EET 2022 + 8: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 8: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 2: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 2: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 8: START 2058110: Thu Nov 24 17:04:51 EET 2022 + 2: START 2058110: Thu Nov 24 17:04:51 EET 2022 +30: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +30: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +30: START 2058110: Thu Nov 24 17:04:51 EET 2022 + 9: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 9: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 9: START 2058110: Thu Nov 24 17:04:51 EET 2022 +22: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +22: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +22: START 2058110: Thu Nov 24 17:04:51 EET 2022 +17: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +17: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +31: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +31: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +17: START 2058110: Thu Nov 24 17:04:51 EET 2022 +31: START 2058110: Thu Nov 24 17:04:51 EET 2022 +28: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +28: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +27: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +28: START 2058110: Thu Nov 24 17:04:51 EET 2022 +27: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +27: START 2058110: Thu Nov 24 17:04:51 EET 2022 +21: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +21: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +21: START 2058110: Thu Nov 24 17:04:51 EET 2022 +18: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +18: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +18: START 2058110: Thu Nov 24 17:04:51 EET 2022 +13: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +13: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +13: START 2058110: Thu Nov 24 17:04:51 EET 2022 + 1: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp + 1: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 + 1: START 2058110: Thu Nov 24 17:04:51 EET 2022 +20: 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 1 --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-1 --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 0 --clip-grad 1.0 --weight-decay 1e-1 --log-interval 10 --save-interval 1000 --eval-interval 1000 --eval-iters 1 --tensorboard-dir tensorboard_83m --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_83m --load checkpoints_83m --data-path /scratch/project_462000119/data/pile/megatron_data/meg-gp +20: t2_pile_text_document --data-impl mmap --split 949,50,1 --deepspeed --deepspeed_config ds_configs/2058110.json --zero-stage 0 +20: START 2058110: Thu Nov 24 17:04:51 EET 2022 +23: +23: +23: ======================= ROCm System Management Interface ======================= +23: ================================= Concise Info ================================= +23: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +23: 0 47.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 2 43.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 4 38.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: 6 39.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +23: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +23: ================================================================================ +23: ============================= 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 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 2 42.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 4 42.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 6: 6 38.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 6: 7 38.0c 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 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 2 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 4 40.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: 6 45.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 3: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 3: ================================================================================ + 3: ============================= 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 41.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 2 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 4 37.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: 6 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +14: 7 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +14: ================================================================================ +14: ============================= 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 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 2 44.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 4 43.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: 6 42.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +19: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +19: ================================================================================ +19: ============================= 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 50.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 2 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 4 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: 6 38.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +26: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +26: ================================================================================ +26: ============================= 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 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 1 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 2 39.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 4 44.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 5 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: 6 39.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +15: 7 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +15: ================================================================================ +15: ============================= 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 49.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 2 41.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 4 48.0c 80.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 7: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 7: 6 39.0c 88.0W 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 ============================== +10: +10: +10: ======================= ROCm System Management Interface ======================= +10: ================================= Concise Info ================================= +10: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +10: 0 42.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 2 42.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 4 45.0c 81.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: 6 40.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +10: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +10: ================================================================================ +10: ============================= 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 43.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 2 39.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 4 42.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: 6 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +24: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +24: ================================================================================ +24: ============================= 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 39.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 1 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 2 33.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 3 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 4 46.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 5 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: 6 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +16: 7 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +16: ================================================================================ +16: ============================= 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 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 2 38.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 3 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 4 42.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: 6 40.0c 86.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 4: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 4: ================================================================================ + 4: ============================= 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 49.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 2 38.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 3 39.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 4 40.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: 6 38.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +29: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +29: ================================================================================ +29: ============================= 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 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 2 42.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 3 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 4 47.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: 6 39.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +25: 7 41.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +25: ================================================================================ +25: ============================= 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 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 2 42.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 4 38.0c 100.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 5 52.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: 6 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 8: 7 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 8: ================================================================================ + 8: ============================= 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 41.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 2 37.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 4 42.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 2: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 2: 6 43.0c 93.0W 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 ============================== +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 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 1 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 2 41.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 4 40.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 5 37.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: 6 38.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +30: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +30: ================================================================================ +30: ============================= 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 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 2 41.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 3 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 4 44.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: 6 47.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 9: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 9: ================================================================================ + 9: ============================= 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 47.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 2 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 3 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 4 45.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 5 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: 6 41.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +22: 7 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +22: ================================================================================ +22: ============================= 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 45.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 1 49.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 2 41.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 4 44.0c 84.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: 6 41.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +31: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +31: ================================================================================ +31: ============================= 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 45.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 1 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 2 40.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 3 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 4 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 5 43.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: 6 43.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +17: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +17: ================================================================================ +17: ============================= 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 43.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 2 42.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 4 39.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: 6 49.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +27: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +27: ================================================================================ +27: ============================= 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 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 2 40.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 4 43.0c 83.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: 6 39.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +28: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +28: ================================================================================ +28: ============================= 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 45.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 1 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 2 35.0c 89.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 4 43.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 5 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: 6 43.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +21: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +21: ================================================================================ +21: ============================= 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 41.0c 94.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 1 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 2 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 3 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 4 43.0c 91.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: 6 46.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +18: 7 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +18: ================================================================================ +18: ============================= 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 44.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 2 38.0c 87.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 4 40.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 5 46.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: 6 37.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +13: 7 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +13: ================================================================================ +13: ============================= 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 43.0c 93.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 1 41.0c 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 40.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 4 40.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% + 1: 5 42.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% + 1: 6 39.0c 91.0W 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 ============================== +20: +20: +20: ======================= ROCm System Management Interface ======================= +20: ================================= Concise Info ================================= +20: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +20: 0 45.0c 85.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 1 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 2 41.0c 95.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 4 45.0c 96.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +20: 5 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +20: 6 44.0c 92.0W 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 ============================== + 5: Launching on nid005365 (5/32), master nid005360 port 9999, GPUs 8, CUDA: True + 0: Launching on nid005360 (0/32), master nid005360 port 9999, GPUs 8, CUDA: True +23: Launching on nid005415 (23/32), master nid005360 port 9999, GPUs 8, CUDA: True + 6: Launching on nid005366 (6/32), master nid005360 port 9999, GPUs 8, CUDA: True +15: Launching on nid005396 (15/32), master nid005360 port 9999, GPUs 8, CUDA: True +27: Launching on nid005419 (27/32), master nid005360 port 9999, GPUs 8, CUDA: True +10: Launching on nid005370 (10/32), master nid005360 port 9999, GPUs 8, CUDA: True +26: Launching on nid005418 (26/32), master nid005360 port 9999, GPUs 8, CUDA: True + 3: Launching on nid005363 (3/32), master nid005360 port 9999, GPUs 8, CUDA: True +19: Launching on nid005411 (19/32), master nid005360 port 9999, GPUs 8, CUDA: True + 8: Launching on nid005368 (8/32), master nid005360 port 9999, GPUs 8, CUDA: True + 2: Launching on nid005362 (2/32), master nid005360 port 9999, GPUs 8, CUDA: True +17: Launching on nid005398 (17/32), master nid005360 port 9999, GPUs 8, CUDA: True +18: Launching on nid005399 (18/32), master nid005360 port 9999, GPUs 8, CUDA: True +28: Launching on nid005420 (28/32), master nid005360 port 9999, GPUs 8, CUDA: True + 4: Launching on nid005364 (4/32), master nid005360 port 9999, GPUs 8, CUDA: True +12: Launching on nid005372 (12/32), master nid005360 port 9999, GPUs 8, CUDA: True +30: Launching on nid005422 (30/32), master nid005360 port 9999, GPUs 8, CUDA: True +20: Launching on nid005412 (20/32), master nid005360 port 9999, GPUs 8, CUDA: True + 1: Launching on nid005361 (1/32), master nid005360 port 9999, GPUs 8, CUDA: True +25: Launching on nid005417 (25/32), master nid005360 port 9999, GPUs 8, CUDA: True +14: Launching on nid005395 (14/32), master nid005360 port 9999, GPUs 8, CUDA: True + 7: Launching on nid005367 (7/32), master nid005360 port 9999, GPUs 8, CUDA: True +31: Launching on nid005423 (31/32), master nid005360 port 9999, GPUs 8, CUDA: True +29: Launching on nid005421 (29/32), master nid005360 port 9999, GPUs 8, CUDA: True +24: Launching on nid005416 (24/32), master nid005360 port 9999, GPUs 8, CUDA: True +16: Launching on nid005397 (16/32), master nid005360 port 9999, GPUs 8, CUDA: True +13: Launching on nid005373 (13/32), master nid005360 port 9999, GPUs 8, CUDA: True +11: Launching on nid005371 (11/32), master nid005360 port 9999, GPUs 8, CUDA: True +22: Launching on nid005414 (22/32), master nid005360 port 9999, GPUs 8, CUDA: True +21: Launching on nid005413 (21/32), master nid005360 port 9999, GPUs 8, CUDA: True + 9: Launching on nid005369 (9/32), master nid005360 port 9999, GPUs 8, CUDA: True + 0: using world size: 256, data-parallel-size: 256, 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 .............................. 256 + 0: data_path ....................................... ['/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_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/2058110.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-1 + 0: kv_channels ..................................... 64 + 0: layer_norm_fusion ............................... True + 0: layernorm_epsilon ............................... 1e-05 + 0: lazy_mpu_init ................................... None + 0: load ............................................ checkpoints_83m + 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 ............................... 0 + 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 ............................. 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_83m + 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_83m + 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 ...................................... 256 + 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: [2022-11-24 17:05:00,020] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +31: > 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: 0.048 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: ninja: no work to do. + 0: >>> done with compiling and loading fused kernels. Compilation time: 21.824 seconds + 0: time to initialize megatron (seconds): 62.926 + 0: [after megatron is initialized] datetime: 2022-11-24 17:05:34 + 0: building GPT model ... + 0: [2022-11-24 17:05:34,977] [INFO] [utils.py:827:see_memory_usage] Before Building Model + 0: [2022-11-24 17:05:34,977] [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: [2022-11-24 17:05:34,977] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.82 GB, percent = 6.5% + 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} + 0: [2022-11-24 17:05:43,888] [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: [2022-11-24 17:05:43,981] [INFO] [utils.py:827:see_memory_usage] After Building Model + 0: [2022-11-24 17:05:43,982] [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: [2022-11-24 17:05:43,982] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 32.83 GB, percent = 6.5% + 0: setting training iterations to 37905 + 0: > learning rate decay style: cosine + 0: DeepSpeed is enabled. + 0: [2022-11-24 17:05:43,983] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown + 0: [2022-11-24 17:06:01,923] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False + 0: [2022-11-24 17:06:01,923] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer + 0: [2022-11-24 17:06:01,924] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer + 0: [2022-11-24 17:06:01,928] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam + 0: [2022-11-24 17:06:01,928] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer + 0: [2022-11-24 17:06:01,972] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer + 0: [2022-11-24 17:06:01,973] [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: [2022-11-24 17:06:01,973] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.53 GB, percent = 6.7% + 1: ninja: no work to do. + 1: Time to load utils op: 0.18718862533569336 seconds + 1: ninja: no work to do. + 7: Time to load utils op: 0.10224294662475586 seconds + 6: Time to load utils op: 0.10393691062927246 seconds + 6: Time to load utils op: 0.10397648811340332 seconds + 1: Time to load utils op: 0.11279129981994629 seconds + 6: Time to load utils op: 0.10380363464355469 seconds + 6: Time to load utils op: 0.1039130687713623 seconds + 6: Time to load utils op: 0.10395669937133789 seconds + 6: Time to load utils op: 0.10418224334716797 seconds + 6: Time to load utils op: 0.10437798500061035 seconds + 6: Time to load utils op: 0.1042931079864502 seconds + 8: Time to load utils op: 0.10297274589538574 secondsTime to load utils op: 0.10309410095214844 seconds + 8: + 8: Time to load utils op: 0.10249543190002441 secondsTime to load utils op: 0.10251641273498535 seconds + 8: + 8: Time to load utils op: 0.10315752029418945 seconds + 8: Time to load utils op: 0.1038045883178711 seconds +13: Time to load utils op: 0.3028717041015625 seconds + 8: Time to load utils op: 0.10391449928283691 seconds + 8: Time to load utils op: 0.10335850715637207 seconds + 9: Time to load utils op: 0.10226750373840332 seconds + 9: Time to load utils op: 0.10248756408691406 seconds + 9: Time to load utils op: 0.10182929039001465 seconds + 9: Time to load utils op: 0.10164475440979004 seconds + 9: Time to load utils op: 0.10178947448730469 seconds + 9: Time to load utils op: 0.10216045379638672 seconds + 9: Time to load utils op: 0.10201382637023926 seconds +10: Time to load utils op: 0.10447025299072266 seconds +11: Time to load utils op: 0.10311412811279297 seconds +10: Time to load utils op: 0.10381317138671875 seconds +10: Time to load utils op: 0.10481381416320801 secondsTime to load utils op: 0.1036376953125 seconds +10: +10: Time to load utils op: 0.10414600372314453 seconds +10: Time to load utils op: 0.10373306274414062 seconds +10: Time to load utils op: 0.10469365119934082 seconds +10: Time to load utils op: 0.10455727577209473 seconds +12: Time to load utils op: 0.10288238525390625 seconds +12: Time to load utils op: 0.10216975212097168 seconds +12: Time to load utils op: 0.10218667984008789 seconds +12: Time to load utils op: 0.10237741470336914 secondsTime to load utils op: 0.10226798057556152 seconds +12: +12: Time to load utils op: 0.1025247573852539 seconds +13: Time to load utils op: 0.10190963745117188 seconds +12: Time to load utils op: 0.10261011123657227 seconds +13: Time to load utils op: 0.10174202919006348 seconds +11: Time to load utils op: 0.10254406929016113 seconds +12: Time to load utils op: 0.10295510292053223 seconds +13: Time to load utils op: 0.10173630714416504 seconds +13: Time to load utils op: 0.10188007354736328 seconds +13: Time to load utils op: 0.10192227363586426 seconds +13: Time to load utils op: 0.1020500659942627 seconds +13: Time to load utils op: 0.1020967960357666 seconds +14: Time to load utils op: 0.10320138931274414 seconds +14: Time to load utils op: 0.10330939292907715 seconds +11: Time to load utils op: 0.10263848304748535 seconds +14: Time to load utils op: 0.10244894027709961 seconds +11: Time to load utils op: 0.10269880294799805 seconds +14: Time to load utils op: 0.10236716270446777 seconds +14: Time to load utils op: 0.10248208045959473 secondsTime to load utils op: 0.10294055938720703 seconds +14: +14: Time to load utils op: 0.10316777229309082 seconds +14: Time to load utils op: 0.10289144515991211 seconds +11: Time to load utils op: 0.10261178016662598 seconds +11: Time to load utils op: 0.10268282890319824 seconds +11: Time to load utils op: 0.10268545150756836 seconds +11: Time to load utils op: 0.10296177864074707 seconds +15: Time to load utils op: 0.10262203216552734 seconds +20: Time to load utils op: 0.3039264678955078 seconds +15: Time to load utils op: 0.10362052917480469 seconds +15: Time to load utils op: 0.1037149429321289 secondsTime to load utils op: 0.1035163402557373 seconds +15: +15: Time to load utils op: 0.10350871086120605 secondsTime to load utils op: 0.10287904739379883 seconds +15: +15: Time to load utils op: 0.10277152061462402 seconds +15: Time to load utils op: 0.10393953323364258 seconds +22: Time to load utils op: 0.3029944896697998 seconds +16: Time to load utils op: 0.1036376953125 seconds +16: Time to load utils op: 0.10356974601745605 seconds +16: Time to load utils op: 0.10361504554748535 seconds +16: Time to load utils op: 0.1036984920501709 seconds +16: Time to load utils op: 0.10370540618896484 seconds +16: Time to load utils op: 0.10385298728942871 seconds +16: Time to load utils op: 0.10384273529052734 seconds +16: Time to load utils op: 0.10375785827636719 seconds +18: Time to load utils op: 0.10378289222717285 secondsTime to load utils op: 0.1038351058959961 secondsTime to load utils op: 0.10383439064025879 seconds +18: +18: +17: Time to load utils op: 0.10474872589111328 seconds +18: Time to load utils op: 0.10377907752990723 seconds +18: Time to load utils op: 0.10378503799438477 seconds +18: Time to load utils op: 0.10347747802734375 seconds +18: Time to load utils op: 0.10324501991271973 seconds +17: Time to load utils op: 0.10494279861450195 seconds +17: Time to load utils op: 0.1049802303314209 seconds +17: Time to load utils op: 0.10510659217834473 seconds +18: Time to load utils op: 0.10504603385925293 seconds +17: Time to load utils op: 0.10521864891052246 secondsTime to load utils op: 0.10524845123291016 seconds +17: +17: Time to load utils op: 0.1050715446472168 seconds +17: Time to load utils op: 0.10540318489074707 seconds +19: Time to load utils op: 0.10378575325012207 secondsTime to load utils op: 0.10369324684143066 seconds +19: +19: Time to load utils op: 0.10366153717041016 seconds +20: Time to load utils op: 0.10190057754516602 seconds +19: Time to load utils op: 0.10299491882324219 seconds +20: Time to load utils op: 0.10164737701416016 seconds +19: Time to load utils op: 0.1031947135925293 seconds +20: Time to load utils op: 0.10177779197692871 seconds +19: Time to load utils op: 0.10352253913879395 seconds +26: Time to load utils op: 0.30295300483703613 seconds +20: Time to load utils op: 0.1018979549407959 seconds +20: Time to load utils op: 0.10199356079101562 seconds +19: Time to load utils op: 0.10349178314208984 seconds +19: Time to load utils op: 0.10393333435058594 seconds +20: Time to load utils op: 0.1017923355102539 seconds +20: Time to load utils op: 0.10171151161193848 seconds +22: Time to load utils op: 0.10181975364685059 secondsTime to load utils op: 0.10191202163696289 seconds +22: +22: Time to load utils op: 0.10231924057006836 seconds +22: Time to load utils op: 0.10166358947753906 seconds +21: Time to load utils op: 0.10448598861694336 secondsTime to load utils op: 0.10406303405761719 seconds +21: Time to load utils op: 0.10445952415466309 seconds +21: +21: Time to load utils op: 0.1046290397644043 secondsTime to load utils op: 0.10465025901794434 seconds +21: +21: Time to load utils op: 0.10460853576660156 seconds +21: Time to load utils op: 0.10495924949645996 seconds +22: Time to load utils op: 0.1018519401550293 seconds +29: Time to load utils op: 0.303025484085083 seconds +21: Time to load utils op: 0.10500550270080566 seconds +22: Time to load utils op: 0.10206007957458496 seconds +22: Time to load utils op: 0.10216116905212402 seconds +23: Time to load utils op: 0.10352516174316406 seconds +23: Time to load utils op: 0.10272431373596191 seconds +24: Time to load utils op: 0.10255861282348633 secondsTime to load utils op: 0.10200786590576172 seconds +24: +24: Time to load utils op: 0.10174846649169922 seconds +24: Time to load utils op: 0.10183215141296387 seconds +24: Time to load utils op: 0.10214519500732422 seconds +24: Time to load utils op: 0.10316824913024902 seconds +24: Time to load utils op: 0.10346508026123047 seconds +24: Time to load utils op: 0.10242843627929688 seconds +23: Time to load utils op: 0.10433197021484375 seconds +23: Time to load utils op: 0.10398006439208984 seconds +23: Time to load utils op: 0.10438179969787598 secondsTime to load utils op: 0.10485601425170898 seconds +23: +23: Time to load utils op: 0.10501265525817871 seconds +23: Time to load utils op: 0.10429000854492188 seconds +26: Time to load utils op: 0.10209488868713379 secondsTime to load utils op: 0.1021568775177002 seconds +26: +26: Time to load utils op: 0.10208725929260254 seconds +26: Time to load utils op: 0.10201454162597656 seconds +26: Time to load utils op: 0.10179781913757324 seconds +25: Time to load utils op: 0.10284590721130371 seconds +25: Time to load utils op: 0.10308241844177246 secondsTime to load utils op: 0.10348176956176758 seconds +25: +26: Time to load utils op: 0.10225915908813477 secondsTime to load utils op: 0.10226774215698242 seconds +26: +25: Time to load utils op: 0.10380077362060547 seconds +25: Time to load utils op: 0.10377907752990723 seconds +25: Time to load utils op: 0.10326218605041504 seconds +25: Time to load utils op: 0.10387420654296875 seconds +25: Time to load utils op: 0.10345625877380371 seconds +27: Time to load utils op: 0.1034088134765625 secondsTime to load utils op: 0.10333657264709473 seconds +27: Time to load utils op: 0.10325169563293457 seconds +27: +27: Time to load utils op: 0.10366964340209961 seconds +27: Time to load utils op: 0.10329508781433105 seconds +27: Time to load utils op: 0.10368537902832031 seconds +27: Time to load utils op: 0.10341715812683105 seconds +27: Time to load utils op: 0.1035165786743164 seconds +29: Time to load utils op: 0.10158824920654297 seconds +29: Time to load utils op: 0.10201191902160645 seconds +29: Time to load utils op: 0.10183286666870117 seconds +29: Time to load utils op: 0.10178208351135254 seconds +29: Time to load utils op: 0.10180091857910156 seconds +29: Time to load utils op: 0.10211706161499023 seconds +28: Time to load utils op: 0.10280632972717285 seconds +28: Time to load utils op: 0.1032562255859375 seconds +28: Time to load utils op: 0.10300230979919434 seconds +29: Time to load utils op: 0.10249495506286621 seconds +28: Time to load utils op: 0.10303282737731934 secondsTime to load utils op: 0.10352587699890137 seconds +28: +28: Time to load utils op: 0.10298371315002441 seconds +28: Time to load utils op: 0.10310840606689453 seconds +28: Time to load utils op: 0.10339045524597168 seconds +30: Time to load utils op: 0.10342073440551758 seconds +30: Time to load utils op: 0.10336542129516602 seconds +30: Time to load utils op: 0.10319972038269043 seconds +31: Time to load utils op: 0.1035614013671875 seconds +30: Time to load utils op: 0.10369873046875 seconds +30: Time to load utils op: 0.1037607192993164 seconds +31: Time to load utils op: 0.10223770141601562 secondsTime to load utils op: 0.10327887535095215 seconds +31: +30: Time to load utils op: 0.10349392890930176 secondsTime to load utils op: 0.10338473320007324 seconds +30: +31: Time to load utils op: 0.1031942367553711 secondsTime to load utils op: 0.10247135162353516 seconds +31: +30: Time to load utils op: 0.10374045372009277 seconds + 0: Time to load utils op: 0.30325818061828613 seconds +31: Time to load utils op: 0.10385894775390625 secondsTime to load utils op: 0.10301756858825684 seconds +31: Time to load utils op: 0.10273861885070801 seconds +31: + 1: Time to load utils op: 0.0006113052368164062 seconds + 1: Time to load utils op: 0.00043702125549316406 seconds + 6: Time to load utils op: 0.00046253204345703125 seconds + 6: Time to load utils op: 0.0003445148468017578 seconds + 6: Time to load utils op: 0.00037288665771484375 seconds + 6: Time to load utils op: 0.00034546852111816406 seconds + 6: Time to load utils op: 0.0003609657287597656 seconds + 6: Time to load utils op: 0.0003464221954345703 seconds + 6: Time to load utils op: 0.0003807544708251953 seconds + 6: Time to load utils op: 0.0003440380096435547 seconds + 7: Time to load utils op: 0.000461578369140625 seconds + 8: Time to load utils op: 0.0004429817199707031 seconds + 8: Time to load utils op: 0.00034737586975097656 seconds + 8: Time to load utils op: 0.0003273487091064453 seconds + 8: Time to load utils op: 0.0003459453582763672 seconds + 8: Time to load utils op: 0.0003306865692138672 seconds + 8: Time to load utils op: 0.0004222393035888672 seconds + 8: Time to load utils op: 0.0003268718719482422 seconds + 8: Time to load utils op: 0.0003113746643066406 seconds + 9: Time to load utils op: 0.00048351287841796875 seconds + 9: Time to load utils op: 0.0003573894500732422 seconds + 9: Time to load utils op: 0.0003662109375 seconds + 9: Time to load utils op: 0.0003056526184082031 seconds + 9: Time to load utils op: 0.0003237724304199219 seconds + 9: Time to load utils op: 0.00031828880310058594 seconds + 9: Time to load utils op: 0.00037479400634765625 seconds +10: Time to load utils op: 0.0005006790161132812 seconds +10: Time to load utils op: 0.00035858154296875 seconds +10: Time to load utils op: 0.0003349781036376953 seconds +10: Time to load utils op: 0.00034046173095703125 seconds +10: Time to load utils op: 0.0003685951232910156 seconds +10: Time to load utils op: 0.00036835670471191406 seconds +10: Time to load utils op: 0.00036263465881347656 seconds +10: Time to load utils op: 0.00033783912658691406 seconds + 0: [2022-11-24 17:06:02,308] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +12: Time to load utils op: 0.00044155120849609375 seconds + 0: [2022-11-24 17:06:02,309] [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: [2022-11-24 17:06:02,309] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.53 GB, percent = 6.7% +13: Time to load utils op: 0.0005486011505126953 seconds +12: Time to load utils op: 0.0004131793975830078 seconds +11: Time to load utils op: 0.0005779266357421875 seconds +12: Time to load utils op: 0.0003788471221923828 secondsTime to load utils op: 0.0003914833068847656 seconds +12: +12: Time to load utils op: 0.00037217140197753906 seconds +12: Time to load utils op: 0.00037217140197753906 seconds +12: Time to load utils op: 0.0003085136413574219 seconds +12: Time to load utils op: 0.00033664703369140625 seconds +11: Time to load utils op: 0.00042724609375 seconds +13: Time to load utils op: 0.0003826618194580078 seconds +11: Time to load utils op: 0.00042510032653808594 seconds +13: Time to load utils op: 0.0004184246063232422 seconds +13: Time to load utils op: 0.00039386749267578125 seconds +13: Time to load utils op: 0.0003540515899658203 seconds +11: Time to load utils op: 0.0004277229309082031 seconds +13: Time to load utils op: 0.0003566741943359375 seconds +11: Time to load utils op: 0.0003941059112548828 secondsTime to load utils op: 0.0004410743713378906 seconds +11: +13: Time to load utils op: 0.000362396240234375 seconds +13: Time to load utils op: 0.00034999847412109375 seconds +11: Time to load utils op: 0.00043272972106933594 seconds +14: Time to load utils op: 0.0004603862762451172 secondsTime to load utils op: 0.0003619194030761719 seconds +14: +14: Time to load utils op: 0.0003666877746582031 seconds +14: Time to load utils op: 0.0003476142883300781 seconds +14: Time to load utils op: 0.0003707408905029297 seconds +14: Time to load utils op: 0.0003597736358642578 seconds +14: Time to load utils op: 0.00037741661071777344 seconds +11: Time to load utils op: 0.0005185604095458984 seconds +14: Time to load utils op: 0.00037407875061035156 seconds +15: Time to load utils op: 0.0004425048828125 seconds +15: Time to load utils op: 0.0003781318664550781 seconds +15: Time to load utils op: 0.00035762786865234375 seconds +15: Time to load utils op: 0.0003552436828613281 seconds +15: Time to load utils op: 0.0003643035888671875 seconds +16: Time to load utils op: 0.0005083084106445312 seconds +15: Time to load utils op: 0.0003476142883300781 seconds +16: Time to load utils op: 0.00031495094299316406 seconds +17: Time to load utils op: 0.0004391670227050781 seconds +16: Time to load utils op: 0.0003380775451660156 seconds +16: Time to load utils op: 0.00032591819763183594 seconds +16: Time to load utils op: 0.00038242340087890625 seconds +17: Time to load utils op: 0.00034689903259277344 seconds +16: Time to load utils op: 0.00036215782165527344 seconds +16: Time to load utils op: 0.00036787986755371094 seconds +17: Time to load utils op: 0.0004038810729980469 seconds +16: Time to load utils op: 0.00036716461181640625 seconds +15: Time to load utils op: 0.00035881996154785156 seconds +15: Time to load utils op: 0.00035834312438964844 seconds +17: Time to load utils op: 0.00034809112548828125 seconds +17: Time to load utils op: 0.00037670135498046875 seconds +17: Time to load utils op: 0.0004024505615234375 seconds +17: Time to load utils op: 0.0003528594970703125 seconds +17: Time to load utils op: 0.0003762245178222656 seconds +20: Time to load utils op: 0.0004892349243164062 seconds +18: Time to load utils op: 0.0003993511199951172 seconds +19: Time to load utils op: 0.00045180320739746094 seconds +18: Time to load utils op: 0.0004355907440185547 seconds +18: Time to load utils op: 0.00039124488830566406 seconds +18: Time to load utils op: 0.00038623809814453125 seconds +18: Time to load utils op: 0.00041103363037109375 seconds +19: Time to load utils op: 0.0003719329833984375 seconds +19: Time to load utils op: 0.0003485679626464844 seconds +18: Time to load utils op: 0.00031757354736328125 seconds +18: Time to load utils op: 0.0004067420959472656 seconds +19: Time to load utils op: 0.00035119056701660156 seconds +18: Time to load utils op: 0.0003898143768310547 seconds +19: Time to load utils op: 0.0003204345703125 seconds +22: Time to load utils op: 0.0005626678466796875 seconds +19: Time to load utils op: 0.00034332275390625 secondsTime to load utils op: 0.000377655029296875 seconds +20: Time to load utils op: 0.0003464221954345703 seconds +19: +19: Time to load utils op: 0.0003762245178222656 seconds +20: Time to load utils op: 0.0003504753112792969 seconds +20: Time to load utils op: 0.00036263465881347656 seconds +20: Time to load utils op: 0.00037932395935058594 seconds +20: Time to load utils op: 0.0003216266632080078 seconds +20: Time to load utils op: 0.0003345012664794922 seconds +20: Time to load utils op: 0.00032138824462890625 seconds +21: Time to load utils op: 0.0004596710205078125 seconds +21: Time to load utils op: 0.0003364086151123047 seconds +21: Time to load utils op: 0.0004291534423828125 secondsTime to load utils op: 0.0004093647003173828 seconds +21: +21: Time to load utils op: 0.0003898143768310547 seconds +21: Time to load utils op: 0.0003783702850341797 seconds +22: Time to load utils op: 0.0003573894500732422 seconds +22: Time to load utils op: 0.0003390312194824219 seconds +22: Time to load utils op: 0.0003266334533691406 seconds +21: Time to load utils op: 0.0003466606140136719 seconds +21: Time to load utils op: 0.0004150867462158203 seconds +22: Time to load utils op: 0.0003440380096435547 seconds +22: Time to load utils op: 0.0003409385681152344 seconds +22: Time to load utils op: 0.0003905296325683594 seconds +22: Time to load utils op: 0.00035190582275390625 seconds +23: Time to load utils op: 0.0004551410675048828 seconds +23: Time to load utils op: 0.00034928321838378906 seconds +23: Time to load utils op: 0.00038552284240722656 secondsTime to load utils op: 0.0003883838653564453 seconds +23: +23: Time to load utils op: 0.0003707408905029297 seconds +23: Time to load utils op: 0.0003638267517089844 seconds +26: Time to load utils op: 0.0005145072937011719 seconds +23: Time to load utils op: 0.0003616809844970703 seconds +23: Time to load utils op: 0.0003407001495361328 seconds +24: Time to load utils op: 0.000518798828125 seconds +24: Time to load utils op: 0.0003268718719482422 seconds +24: Time to load utils op: 0.0004930496215820312 seconds +24: Time to load utils op: 0.0003039836883544922 seconds +25: Time to load utils op: 0.00044989585876464844 seconds +24: Time to load utils op: 0.000324249267578125 seconds +25: Time to load utils op: 0.0003390312194824219 seconds +24: Time to load utils op: 0.0003952980041503906 seconds +24: Time to load utils op: 0.00038170814514160156 seconds +25: Time to load utils op: 0.00035500526428222656 seconds +24: Time to load utils op: 0.0003750324249267578 seconds +25: Time to load utils op: 0.00031256675720214844 seconds +26: Time to load utils op: 0.00034737586975097656 seconds +25: Time to load utils op: 0.00033974647521972656 seconds +26: Time to load utils op: 0.000339508056640625 seconds +26: Time to load utils op: 0.0003707408905029297 seconds +25: Time to load utils op: 0.00034880638122558594 seconds +26: Time to load utils op: 0.00034809112548828125 seconds +25: Time to load utils op: 0.00034046173095703125 secondsTime to load utils op: 0.000347137451171875 seconds +25: +26: Time to load utils op: 0.00036644935607910156 seconds +26: Time to load utils op: 0.0003502368927001953 seconds +26: Time to load utils op: 0.0003247261047363281 seconds +27: Time to load utils op: 0.0004258155822753906 seconds +27: Time to load utils op: 0.0003771781921386719 seconds +29: Time to load utils op: 0.0006246566772460938 seconds +27: Time to load utils op: 0.0003540515899658203 seconds +27: Time to load utils op: 0.0003647804260253906 seconds +27: Time to load utils op: 0.0003609657287597656 seconds +27: Time to load utils op: 0.00035452842712402344 seconds +28: Time to load utils op: 0.00046062469482421875 seconds +27: Time to load utils op: 0.00034332275390625 secondsTime to load utils op: 0.0003399848937988281 seconds +27: +28: Time to load utils op: 0.00032401084899902344 seconds +28: Time to load utils op: 0.00033545494079589844 seconds +28: Time to load utils op: 0.00036215782165527344 seconds +28: Time to load utils op: 0.0003592967987060547 seconds +28: Time to load utils op: 0.00032973289489746094 seconds +29: Time to load utils op: 0.0003516674041748047 seconds +28: Time to load utils op: 0.0003514289855957031 seconds +29: Time to load utils op: 0.0003757476806640625 seconds +28: Time to load utils op: 0.0003261566162109375 seconds +29: Time to load utils op: 0.0003800392150878906 seconds +29: Time to load utils op: 0.00034999847412109375 seconds +29: Time to load utils op: 0.00036644935607910156 seconds +29: Time to load utils op: 0.0004260540008544922 seconds +29: Time to load utils op: 0.00040721893310546875 seconds +30: Time to load utils op: 0.0005011558532714844 seconds +30: Time to load utils op: 0.00036644935607910156 seconds +30: Time to load utils op: 0.0003516674041748047 seconds +30: Time to load utils op: 0.0003783702850341797 seconds +30: Time to load utils op: 0.0003542900085449219 seconds +30: Time to load utils op: 0.00034332275390625 seconds +31: Time to load utils op: 0.0004143714904785156 seconds +30: Time to load utils op: 0.0003638267517089844 seconds +30: Time to load utils op: 0.0004146099090576172 seconds +31: Time to load utils op: 0.0003418922424316406 seconds +31: Time to load utils op: 0.00035071372985839844 seconds +31: Time to load utils op: 0.0003695487976074219 seconds +31: Time to load utils op: 0.00035834312438964844 seconds +31: Time to load utils op: 0.00035071372985839844 seconds +31: Time to load utils op: 0.00034046173095703125 seconds +31: Time to load utils op: 0.0003273487091064453 seconds + 1: Time to load utils op: 0.2028505802154541 seconds + 1: Time to load utils op: 0.2033090591430664 secondsTime to load utils op: 0.20256447792053223 seconds + 1: + 1: Time to load utils op: 0.20328474044799805 seconds + 0: Time to load utils op: 0.20386385917663574 seconds + 1: Time to load utils op: 0.20242691040039062 secondsTime to load utils op: 0.2023763656616211 seconds + 1: + 0: Time to load utils op: 0.2039327621459961 seconds + 0: Time to load utils op: 0.2026958465576172 seconds + 0: Time to load utils op: 0.20410847663879395 seconds + 0: Time to load utils op: 0.20182037353515625 seconds + 0: Time to load utils op: 0.20433425903320312 seconds + 0: Time to load utils op: 0.20244050025939941 seconds + 2: Time to load utils op: 0.20364999771118164 secondsTime to load utils op: 0.20330047607421875 seconds + 2: + 2: Time to load utils op: 0.20362567901611328 secondsTime to load utils op: 0.2038130760192871 seconds + 2: + 2: Time to load utils op: 0.20351386070251465 seconds + 2: Time to load utils op: 0.20355558395385742 seconds + 2: Time to load utils op: 0.20386886596679688 seconds + 2: Time to load utils op: 0.2039339542388916 seconds + 7: Time to load utils op: 0.4042685031890869 seconds + 3: Time to load utils op: 0.20391511917114258 seconds + 3: Time to load utils op: 0.20287346839904785 secondsTime to load utils op: 0.20297884941101074 seconds + 3: + 3: Time to load utils op: 0.20337653160095215 seconds + 4: Time to load utils op: 0.20306181907653809 seconds + 3: Time to load utils op: 0.20354080200195312 seconds + 3: Time to load utils op: 0.20354080200195312 seconds + 4: Time to load utils op: 0.20313143730163574 secondsTime to load utils op: 0.20348381996154785 secondsTime to load utils op: 0.20278549194335938 seconds + 4: + 4: + 4: Time to load utils op: 0.20426011085510254 secondsTime to load utils op: 0.20412969589233398 seconds + 4: + 3: Time to load utils op: 0.20434021949768066 secondsTime to load utils op: 0.204054594039917 seconds + 3: + 4: Time to load utils op: 0.20400762557983398 seconds + 4: Time to load utils op: 0.20319509506225586 seconds + 9: Time to load utils op: 0.40308141708374023 seconds + 5: Time to load utils op: 0.20430517196655273 seconds + 5: Time to load utils op: 0.20383119583129883 secondsTime to load utils op: 0.2034909725189209 seconds + 5: + 5: Time to load utils op: 0.20336008071899414 seconds + 5: Time to load utils op: 0.20427584648132324 seconds + 5: Time to load utils op: 0.20400595664978027 seconds + 5: Time to load utils op: 0.204911470413208 seconds + 7: Time to load utils op: 0.20184111595153809 seconds + 5: Time to load utils op: 0.2050471305847168 seconds + 7: Time to load utils op: 0.2021167278289795 seconds + 7: Time to load utils op: 0.20236968994140625 seconds + 7: Time to load utils op: 0.2021632194519043 seconds + 7: Time to load utils op: 0.2022111415863037 seconds + 7: Time to load utils op: 0.20241332054138184 seconds + 1: Time to load utils op: 0.00032830238342285156 seconds + 1: Time to load utils op: 0.00036215782165527344 seconds + 1: Time to load utils op: 0.00040841102600097656 seconds + 1: Time to load utils op: 0.0003731250762939453 seconds + 0: [2022-11-24 17:06:02,352] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 + 1: Time to load utils op: 0.0003719329833984375 seconds + 1: Time to load utils op: 0.00040912628173828125 seconds + 0: [2022-11-24 17:06:02,353] [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: [2022-11-24 17:06:02,353] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.53 GB, percent = 6.7% + 0: Time to load utils op: 0.0005517005920410156 seconds + 0: Time to load utils op: 0.0005788803100585938 seconds + 0: Time to load utils op: 0.0005762577056884766 seconds + 0: Time to load utils op: 0.0004189014434814453 seconds + 0: Time to load utils op: 0.0004131793975830078 seconds + 0: Time to load utils op: 0.0005707740783691406 seconds + 0: Time to load utils op: 0.00043654441833496094 seconds + 2: Time to load utils op: 0.0004532337188720703 seconds + 2: Time to load utils op: 0.000339508056640625 seconds + 2: Time to load utils op: 0.0004284381866455078 seconds + 2: Time to load utils op: 0.0003848075866699219 seconds + 2: Time to load utils op: 0.00039386749267578125 seconds + 2: Time to load utils op: 0.00038504600524902344 seconds + 2: Time to load utils op: 0.00038909912109375 seconds + 2: Time to load utils op: 0.0003819465637207031 seconds + 9: Time to load utils op: 0.0003821849822998047 seconds + 3: Time to load utils op: 0.0003647804260253906 secondsTime to load utils op: 0.00045752525329589844 secondsTime to load utils op: 0.00032806396484375 seconds + 3: + 3: + 3: Time to load utils op: 0.0004076957702636719 seconds + 3: Time to load utils op: 0.00036644935607910156 seconds + 3: Time to load utils op: 0.00033020973205566406 seconds + 7: Time to load utils op: 0.0004296302795410156 seconds + 3: Time to load utils op: 0.000362396240234375 seconds + 3: Time to load utils op: 0.00035381317138671875 seconds + 4: Time to load utils op: 0.0004544258117675781 secondsTime to load utils op: 0.00048232078552246094 seconds + 4: + 4: Time to load utils op: 0.0003097057342529297 seconds + 4: Time to load utils op: 0.0003311634063720703 seconds + 4: Time to load utils op: 0.00037980079650878906 seconds + 4: Time to load utils op: 0.0004112720489501953 seconds + 4: Time to load utils op: 0.0003635883331298828 seconds + 4: Time to load utils op: 0.0003521442413330078 seconds + 5: Time to load utils op: 0.00042557716369628906 seconds + 5: Time to load utils op: 0.00032973289489746094 seconds + 5: Time to load utils op: 0.0003452301025390625 seconds + 5: Time to load utils op: 0.00042247772216796875 seconds + 7: Time to load utils op: 0.0003743171691894531 seconds + 5: Time to load utils op: 0.0003788471221923828 seconds + 5: Time to load utils op: 0.0003769397735595703 seconds + 7: Time to load utils op: 0.0003769397735595703 seconds + 7: Time to load utils op: 0.0003771781921386719 seconds + 5: Time to load utils op: 0.00037217140197753906 seconds + 5: Time to load utils op: 0.00036644935607910156 seconds + 7: Time to load utils op: 0.0003819465637207031 seconds + 7: Time to load utils op: 0.0003895759582519531 seconds + 7: Time to load utils op: 0.00045800209045410156 seconds + 0: [2022-11-24 17:06:02,400] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 + 0: [2022-11-24 17:06:02,400] [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: [2022-11-24 17:06:02,400] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.67 GB, percent = 6.7% + 0: [2022-11-24 17:06:02,436] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 + 0: [2022-11-24 17:06:02,437] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 17:06:02,437] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.67 GB, percent = 6.7% + 0: [2022-11-24 17:06:02,469] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 + 0: [2022-11-24 17:06:02,469] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 17:06:02,469] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.67 GB, percent = 6.7% + 0: [2022-11-24 17:06:02,503] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 + 0: [2022-11-24 17:06:02,503] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 17:06:02,503] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.67 GB, percent = 6.7% + 0: [2022-11-24 17:06:02,534] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer + 0: [2022-11-24 17:06:02,535] [INFO] [utils.py:828:see_memory_usage] MA 0.46 GB Max_MA 0.46 GB CA 0.58 GB Max_CA 1 GB + 0: [2022-11-24 17:06:02,535] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.67 GB, percent = 6.7% + 0: [2022-11-24 17:06:02,571] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer + 0: [2022-11-24 17:06:02,572] [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: [2022-11-24 17:06:02,572] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.67 GB, percent = 6.7% + 0: [2022-11-24 17:06:02,603] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer + 0: [2022-11-24 17:06:02,603] [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: [2022-11-24 17:06:02,603] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 33.67 GB, percent = 6.7% + 0: [2022-11-24 17:06:02,604] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam + 0: [2022-11-24 17:06:02,604] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler + 0: [2022-11-24 17:06:02,604] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = + 0: [2022-11-24 17:06:02,604] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0002, 0.0002, 0.0002], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] + 0: [2022-11-24 17:06:02,604] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: + 0: [2022-11-24 17:06:02,604] [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: [2022-11-24 17:06:02,604] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} + 0: [2022-11-24 17:06:02,604] [INFO] [config.py:1011:print] amp_enabled .................. False + 0: [2022-11-24 17:06:02,604] [INFO] [config.py:1011:print] amp_params ................... False + 0: [2022-11-24 17:06:02,605] [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: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] bfloat16_enabled ............. True + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] comms_config ................. + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] communication_data_type ...... None + 0: [2022-11-24 17:06:02,605] [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: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] curriculum_enabled ........... False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] curriculum_params ............ False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] dataloader_drop_last ......... False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] disable_allgather ............ False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] dump_state ................... False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] elasticity_enabled ........... False + 0: [2022-11-24 17:06:02,605] [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: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] fp16_auto_cast ............... None + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] fp16_enabled ................. False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] global_rank .................. 0 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] load_universal_checkpoint .... False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] loss_scale ................... 1.0 + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] memory_breakdown ............. False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] monitor_config ............... + 0: [2022-11-24 17:06:02,605] [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: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False + 0: [2022-11-24 17:06:02,605] [INFO] [config.py:1011:print] optimizer_name ............... None + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] optimizer_params ............. None + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] pld_enabled .................. False + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] pld_params ................... False + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] prescale_gradients ........... False + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] scheduler_name ............... None + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] scheduler_params ............. None + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] sparse_attention ............. None + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] steps_per_print .............. 2000 + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] train_batch_size ............. 256 + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 1 + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] use_node_local_storage ....... False + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] world_size ................... 256 + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False + 0: [2022-11-24 17:06:02,606] [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: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] zero_enabled ................. False + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 + 0: [2022-11-24 17:06:02,606] [INFO] [config.py:996:print_user_config] json = { + 0: "train_micro_batch_size_per_gpu": 1, + 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: 0.0004143714904785156 seconds + 0: [2022-11-24 17:06:02,607] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=1 + 0: [2022-11-24 17:06:02,617] [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: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,625] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,626] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,627] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 5: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +29: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +29: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +12: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 8: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,628] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +28: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +20: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 8: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +30: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +28: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +26: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +24: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +26: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +31: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +19: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +18: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +14: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +19: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +15: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +20: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... + 9: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +22: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +24: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +12: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 6: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +27: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 4: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +23: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +15: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,629] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +30: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +14: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +18: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 7: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +23: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +16: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 3: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 9: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +10: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +11: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 2: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,630] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,631] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/mp_rank_00_model_states.pt. + 5: [2022-11-24 17:06:02,632] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,633] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,651] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,652] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,653] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,654] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,655] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,656] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +19: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,657] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,658] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +14: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +29: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +17: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,659] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +12: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +22: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +31: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,660] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,661] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +26: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +21: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +20: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +13: [2022-11-24 17:06:02,662] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +23: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +30: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +28: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,663] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +15: [2022-11-24 17:06:02,664] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +10: [2022-11-24 17:06:02,665] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +25: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +27: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +18: [2022-11-24 17:06:02,666] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +24: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,667] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,668] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,669] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +11: [2022-11-24 17:06:02,670] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt... +16: [2022-11-24 17:06:02,676] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,677] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,678] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,679] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,680] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,681] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,682] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,683] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,684] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,685] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,686] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,687] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,688] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +31: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,689] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,690] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +19: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,691] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,692] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +20: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +22: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,693] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +23: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +30: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +10: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +21: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +28: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,694] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,695] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,696] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +15: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +25: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,697] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +16: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +13: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +27: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +24: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +17: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,698] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +12: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +26: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,699] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +29: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,700] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,701] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +14: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,702] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. +18: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_01-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,703] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,704] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,705] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,706] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,707] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,708] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,709] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,710] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,711] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,712] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +21: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +15: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +30: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,713] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +28: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +19: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +20: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,714] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +16: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,715] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,716] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,717] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +14: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +25: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +10: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +29: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,718] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +22: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +13: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +17: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +14: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +27: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,719] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +24: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +18: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +10: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,720] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +30: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +22: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,721] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +27: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +11: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +11: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,722] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +16: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,723] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,724] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +13: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +25: [2022-11-24 17:06:02,725] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +24: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +17: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +21: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +28: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +23: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +23: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,726] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +15: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +31: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,727] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +29: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +12: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,728] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... +26: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,729] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +16: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,731] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +26: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +18: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +28: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +21: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +11: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +31: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +13: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,734] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_03-model_00-model_states.pt. +20: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +19: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,736] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +17: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +27: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +20: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +28: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +13: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +31: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +10: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +27: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +21: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +27: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +10: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +17: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +13: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +10: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +18: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +30: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +21: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,741] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +18: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +30: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +12: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +20: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +25: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +17: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +13: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +20: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +15: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +14: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +20: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +31: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +11: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +14: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +31: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,730] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,732] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,733] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,735] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,737] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,738] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,739] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,740] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,742] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +23: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +26: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt... +29: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +12: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +23: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +26: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +29: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +12: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +14: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +29: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +31: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +23: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +26: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +14: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +31: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +14: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +31: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,795] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 248 +12: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +23: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +23: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +12: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +29: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,797] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 213 +31: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +26: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: > using checkpoint value 0.0002 for learning rate + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: > using checkpoint value 2e-05 for minimum learning rate + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: > using checkpoint value 0 for warmup iterations +12: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: > using checkpoint value 9703701 for total number of iterations + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: > using checkpoint value cosine for decay style +12: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,801] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 99 + 6: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,802] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 41 +29: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +14: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,804] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 96 +12: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,804] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 98 + 6: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 44 +11: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 54 +26: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 50 + 6: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:06:02,806] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 208 +23: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +26: [2022-11-24 17:06:02,806] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 209 + 3: [2022-11-24 17:06:02,807] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 25 +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,807] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 24 +12: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,807] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 0 + 5: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:06:02,808] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 92 +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,806] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 251 + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,807] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 253 +12: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,809] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 5 +26: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,810] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 41 + 7: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +14: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,810] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 29 +14: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,810] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 31 +14: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,811] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 101 +14: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +29: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +26: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +29: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +31: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +26: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,815] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 59 +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,815] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 113 + 1: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +12: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:06:02,815] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 187 + 7: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,815] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 190 +23: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +12: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +31: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,815] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 112 +14: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +14: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,818] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 237 +29: [2022-11-24 17:06:02,818] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 235 + 1: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +26: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,820] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 233 +29: [2022-11-24 17:06:02,820] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 239 +11: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +31: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +12: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,810] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 8 +19: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +14: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:02,821] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 186 +14: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,814] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 14 +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +26: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,822] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 185 +26: [2022-11-24 17:06:02,822] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 215 + 1: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +26: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +29: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 184 +12: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +26: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 211 +14: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 116 +26: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 255 +31: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 114 +31: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +29: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,824] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 254 +11: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,816] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 10 +19: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,816] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 11 +19: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +23: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +29: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 49 + 6: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 55 +29: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +26: [2022-11-24 17:06:02,826] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 213 + 7: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +26: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +12: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +23: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +31: [2022-11-24 17:06:02,829] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 250 +14: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,829] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 189 +31: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,829] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 249 + 6: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +19: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +19: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,831] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 90 + 0: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +29: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +29: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +14: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +14: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +12: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +26: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +14: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,833] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 210 +14: [2022-11-24 17:06:02,833] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 117 +12: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +14: [2022-11-24 17:06:02,833] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 115 + 7: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,833] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 119 +29: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,833] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 255 + 0: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +23: [2022-11-24 17:06:02,833] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 188 + 5: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +12: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +29: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,835] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 0 +29: [2022-11-24 17:06:02,835] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 232 +29: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: checkpoint version 3.0 +14: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,835] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 238 +12: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +29: [2022-11-24 17:06:02,835] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 234 +19: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +14: [2022-11-24 17:06:02,835] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 118 +19: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,836] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 92 +11: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +29: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:06:02,837] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 42 +11: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,807] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 159 + 2: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,810] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 156 + 5: [2022-11-24 17:06:02,838] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 45 +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +19: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,839] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 5 +12: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +29: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +19: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +29: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +12: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +19: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +19: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +19: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,840] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 103 +19: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,825] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 154 + 2: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +19: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 157 +19: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 155 + 2: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +19: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 152 + 2: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 153 + 2: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +12: [2022-11-24 17:06:02,841] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 102 +19: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +19: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +19: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +19: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +19: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +19: [2022-11-24 17:06:02,833] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 158 + 1: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,841] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 99 + 5: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,842] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 13 + 2: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +12: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,843] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 12 + 2: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:06:02,844] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 30 + 2: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,844] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 26 + 2: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,844] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 28 + 2: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,844] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 27 + 2: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,844] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 9 + 2: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +12: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:06:02,845] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 100 + 1: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +12: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +29: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,846] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 236 + 2: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,810] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 23 +15: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +12: [2022-11-24 17:06:02,846] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 97 + 2: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,846] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 50 + 2: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,811] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 21 + 5: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 3: [2022-11-24 17:06:02,848] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 25 + 2: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +15: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,851] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 8 +15: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +15: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +31: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +31: [2022-11-24 17:06:02,851] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 252 +23: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +23: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,852] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 15 + 6: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,852] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 53 +15: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,852] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 51 + 2: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,804] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 123 + 5: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 120 +15: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +14: [2022-11-24 17:06:02,855] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 113 +15: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,855] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 59 +15: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +15: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +23: [2022-11-24 17:06:02,855] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 190 +15: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,856] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 48 +15: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,832] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 123 +31: [2022-11-24 17:06:02,857] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 248 +15: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,858] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 52 + 2: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +23: [2022-11-24 17:06:02,858] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 189 +15: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +12: [2022-11-24 17:06:02,858] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 98 +15: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 3: [2022-11-24 17:06:02,858] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 24 +15: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +12: [2022-11-24 17:06:02,858] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 101 +15: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +23: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +15: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +15: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,858] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 127 +27: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,860] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 121 +27: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +31: [2022-11-24 17:06:02,861] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 254 +27: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +27: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +27: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,801] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 221 +20: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +14: [2022-11-24 17:06:02,862] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 112 + 5: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +15: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,863] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 47 + 7: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,863] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 43 + 7: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +15: [2022-11-24 17:06:02,863] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 125 + 7: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +11: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +15: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +27: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,865] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 62 +27: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,865] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 58 +27: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,826] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 221 +20: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,867] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 13 + 2: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +27: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,849] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 218 +20: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,850] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 223 +20: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,869] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 120 +27: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +27: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,854] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 219 +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 6: [2022-11-24 17:06:02,870] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 51 + 2: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +27: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +27: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +27: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 6: [2022-11-24 17:06:02,871] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 54 +27: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,871] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 208 +11: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +27: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +27: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +27: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:06:02,872] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 222 + 2: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +27: [2022-11-24 17:06:02,872] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 217 +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,873] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 12 +20: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +20: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,799] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 167 +22: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,799] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 160 +20: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,874] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 20 +20: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +20: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +27: [2022-11-24 17:06:02,874] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 216 +20: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +20: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +15: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +26: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +26: [2022-11-24 17:06:02,875] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 212 +20: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +20: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,875] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 40 +11: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +20: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,876] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 19 + 5: [2022-11-24 17:06:02,876] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 46 +20: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,877] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 61 +20: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +15: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +27: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +27: [2022-11-24 17:06:02,877] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 220 +20: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +20: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,877] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 18 + 7: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +20: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 165 +22: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 161 +22: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +20: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,842] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 166 +22: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +20: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,847] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 164 +22: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +20: [2022-11-24 17:06:02,847] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 162 +22: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +20: [2022-11-24 17:06:02,848] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 163 +22: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +20: [2022-11-24 17:06:02,863] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 167 +22: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,879] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 9 +22: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,880] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 22 +22: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +22: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +15: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 1: [2022-11-24 17:06:02,880] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 15 +22: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +15: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +15: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +12: [2022-11-24 17:06:02,881] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 96 +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +22: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +26: [2022-11-24 17:06:02,882] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 209 +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +22: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +22: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,883] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,883] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 16 +22: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,883] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +22: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +14: [2022-11-24 17:06:02,884] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 114 + 7: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +15: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +22: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,800] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 180 +24: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 178 +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 176 +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +26: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +26: [2022-11-24 17:06:02,886] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 214 +15: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +31: [2022-11-24 17:06:02,886] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 252 +22: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +27: [2022-11-24 17:06:02,886] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 218 +22: [2022-11-24 17:06:02,810] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 180 +22: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,817] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 181 +22: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 17:06:02,817] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 177 +24: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +22: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +22: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,887] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,887] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 57 +22: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +22: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,887] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 44 +22: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +22: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 183 +24: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +22: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 179 +24: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +22: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +22: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +15: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +22: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +22: [2022-11-24 17:06:02,843] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 182 + 0: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +22: [2022-11-24 17:06:02,861] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 181 +24: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,870] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 176 +24: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +22: [2022-11-24 17:06:02,870] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 178 +24: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +10: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +24: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +24: [2022-11-24 17:06:02,796] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 196 +10: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,890] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 124 +24: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 1: [2022-11-24 17:06:02,890] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 10 +24: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,802] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 196 +10: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +10: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +24: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,891] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 60 + 7: [2022-11-24 17:06:02,891] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 56 +24: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +24: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,891] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 63 +24: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,891] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +15: [2022-11-24 17:06:02,891] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 122 +24: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,893] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 17 +24: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,893] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,894] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 61 +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +24: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,844] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 192 +10: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,845] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 199 +10: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +24: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +24: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +24: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +24: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,896] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +24: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,880] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 198 +24: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:06:02,897] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 126 +24: [2022-11-24 17:06:02,880] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 197 +24: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +24: [2022-11-24 17:06:02,881] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 195 +10: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +24: [2022-11-24 17:06:02,887] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,887] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 193 +10: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +24: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +24: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +11: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +24: [2022-11-24 17:06:02,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:06:02,896] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +24: [2022-11-24 17:06:02,896] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 194 +10: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,804] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 84 + 4: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,804] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 85 + 4: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +10: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +10: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,899] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,899] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,900] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,900] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 47 +10: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +23: [2022-11-24 17:06:02,901] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 188 +10: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +10: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,901] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 16 +10: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +10: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,841] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 84 + 4: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,843] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 81 + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,843] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 82 +10: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +10: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +10: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +10: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +10: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,858] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 87 + 4: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +10: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +10: [2022-11-24 17:06:02,859] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 86 + 4: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +10: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +10: [2022-11-24 17:06:02,860] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 83 + 4: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +10: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,863] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 80 + 4: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +10: [2022-11-24 17:06:02,881] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 85 + 4: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:06:02,905] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 124 + 4: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 5: [2022-11-24 17:06:02,905] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 43 + 4: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,905] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +11: [2022-11-24 17:06:02,905] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +27: [2022-11-24 17:06:02,906] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 223 + 4: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,906] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,906] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 90 +14: [2022-11-24 17:06:02,906] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 115 +11: [2022-11-24 17:06:02,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,906] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +14: [2022-11-24 17:06:02,906] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 117 + 4: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +31: [2022-11-24 17:06:02,907] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 253 + 4: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,907] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,802] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 34 + 8: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +23: [2022-11-24 17:06:02,907] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 187 + 4: [2022-11-24 17:06:02,803] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 38 + 4: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 7: [2022-11-24 17:06:02,908] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 63 + 4: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:06:02,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,908] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,812] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 32 + 8: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,812] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 33 + 4: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,909] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 7 + 0: [2022-11-24 17:06:02,909] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 2 + 4: [2022-11-24 17:06:02,816] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 37 + 4: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,909] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 91 + 4: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,909] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,909] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,824] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 39 + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,824] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 36 + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:06:02,826] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 35 + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +26: [2022-11-24 17:06:02,910] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 212 + 4: [2022-11-24 17:06:02,826] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 38 + 4: [2022-11-24 17:06:02,830] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 34 + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,838] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 39 + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 4: [2022-11-24 17:06:02,853] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 36 + 8: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,910] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,910] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,911] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +11: [2022-11-24 17:06:02,911] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,800] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 68 +16: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,912] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,912] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,805] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 68 +16: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +20: [2022-11-24 17:06:02,912] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 160 + 8: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,810] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 69 + 8: [2022-11-24 17:06:02,810] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 70 +16: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:06:02,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,913] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:06:02,913] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 214 + 8: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,822] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 67 +16: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,822] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 66 +16: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,825] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 71 +16: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,825] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 65 +16: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,914] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,914] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,835] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 64 + 8: [2022-11-24 17:06:02,896] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 71 +16: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,906] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 65 +16: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,915] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 69 +16: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +11: [2022-11-24 17:06:02,915] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,915] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 45 +16: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,915] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,916] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 94 +16: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +11: [2022-11-24 17:06:02,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,795] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 132 +16: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,916] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:06:02,916] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 14 +16: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +11: [2022-11-24 17:06:02,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,916] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,917] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,917] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 1 +16: [2022-11-24 17:06:02,808] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 132 +16: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,917] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 3 +16: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +16: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,917] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 6 +16: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,917] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 60 +16: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,917] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 56 +16: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,918] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +16: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 2: [2022-11-24 17:06:02,919] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 23 +16: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,919] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +11: [2022-11-24 17:06:02,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,919] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +11: [2022-11-24 17:06:02,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +11: [2022-11-24 17:06:02,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:06:02,920] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,838] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 131 +18: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:06:02,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,838] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 134 +16: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +16: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,920] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:06:02,921] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 4 +16: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +16: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,792] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 144 +16: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +16: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +16: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,873] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +11: [2022-11-24 17:06:02,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,873] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,922] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +16: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,805] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 144 +16: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,922] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 95 +16: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +11: [2022-11-24 17:06:02,923] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 88 +16: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +16: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +16: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +16: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,886] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 133 +18: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,923] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +16: [2022-11-24 17:06:02,890] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 128 +18: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +16: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +16: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,893] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 130 +18: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +16: [2022-11-24 17:06:02,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +16: [2022-11-24 17:06:02,893] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +16: [2022-11-24 17:06:02,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +31: [2022-11-24 17:06:02,924] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 249 +16: [2022-11-24 17:06:02,895] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:06:02,896] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 135 +18: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +16: [2022-11-24 17:06:02,896] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 129 +18: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,830] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 147 +25: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +18: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +18: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 5: [2022-11-24 17:06:02,926] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 42 +18: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +18: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,862] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 147 +25: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +18: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,863] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +18: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +18: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +18: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +18: [2022-11-24 17:06:02,880] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,885] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,886] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 151 +25: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +18: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +18: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,889] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,890] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 146 +25: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +18: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,890] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,891] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,892] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,894] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,894] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,897] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +11: [2022-11-24 17:06:02,929] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +18: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,898] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,900] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +18: [2022-11-24 17:06:02,900] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 145 +25: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +18: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +18: [2022-11-24 17:06:02,901] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +11: [2022-11-24 17:06:02,930] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 89 +18: [2022-11-24 17:06:02,902] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:06:02,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +18: [2022-11-24 17:06:02,904] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 148 +25: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,904] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:06:02,904] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,905] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 149 +25: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,907] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +18: [2022-11-24 17:06:02,907] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 150 +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +18: [2022-11-24 17:06:02,914] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 146 +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_04-model_00-model_states.pt. +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,800] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 202 +30: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,803] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 205 +30: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +25: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +23: [2022-11-24 17:06:02,931] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +23: [2022-11-24 17:06:02,931] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +25: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,933] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 67 +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +25: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +25: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,839] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 202 +30: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +25: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +14: [2022-11-24 17:06:02,934] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 119 +25: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 4: [2022-11-24 17:06:02,934] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 37 +25: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,846] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +25: [2022-11-24 17:06:02,853] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,853] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 201 +30: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +25: [2022-11-24 17:06:02,854] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 206 +30: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,855] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 203 +30: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +25: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +25: [2022-11-24 17:06:02,856] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 207 +30: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +25: [2022-11-24 17:06:02,857] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 204 +30: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +25: [2022-11-24 17:06:02,873] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 205 +30: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +25: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +25: [2022-11-24 17:06:02,878] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 200 +30: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,896] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 201 +30: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +25: [2022-11-24 17:06:02,901] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 206 +30: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +25: [2022-11-24 17:06:02,935] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 200 +30: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +30: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,802] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 244 +30: [2022-11-24 17:06:02,802] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 242 + 9: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +30: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,809] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 244 + 9: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +29: [2022-11-24 17:06:02,937] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 235 +30: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +30: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +29: [2022-11-24 17:06:02,938] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 237 +30: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,939] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 118 +30: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,839] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 247 + 9: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +30: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +30: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +30: [2022-11-24 17:06:02,850] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 242 + 9: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +30: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,860] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +30: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +30: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,866] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +15: [2022-11-24 17:06:02,941] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 127 +30: [2022-11-24 17:06:02,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +30: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,868] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 240 + 9: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +30: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,869] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +11: [2022-11-24 17:06:02,941] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 94 +30: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,870] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,871] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +30: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,876] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,877] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,878] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,878] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 241 + 9: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +30: [2022-11-24 17:06:02,878] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 246 + 9: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:06:02,879] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,800] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 78 +30: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +30: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,800] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 72 +30: [2022-11-24 17:06:02,882] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,884] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,884] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 245 + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,886] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +30: [2022-11-24 17:06:02,888] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +30: [2022-11-24 17:06:02,888] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 243 + 9: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +30: [2022-11-24 17:06:02,898] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 247 + 9: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +30: [2022-11-24 17:06:02,917] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 243 + 9: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,827] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 78 +17: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +24: [2022-11-24 17:06:02,944] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 195 + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +25: [2022-11-24 17:06:02,944] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 203 + 9: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,834] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 79 +17: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,834] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 75 +17: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 8: [2022-11-24 17:06:02,945] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 66 + 9: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,852] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,856] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 77 +17: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,857] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 76 +17: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,859] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 74 +17: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,863] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 72 +17: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,875] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 79 +17: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,881] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,882] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 73 +17: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 9: [2022-11-24 17:06:02,887] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 74 +17: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 9: [2022-11-24 17:06:02,916] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 75 +17: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +17: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +22: [2022-11-24 17:06:02,947] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 177 +17: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +17: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +17: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,764] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +14: [2022-11-24 17:06:02,949] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 116 +17: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +17: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +11: [2022-11-24 17:06:02,950] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 88 +17: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +17: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. + 8: [2022-11-24 17:06:02,951] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 70 +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +17: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,818] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 136 +17: [2022-11-24 17:06:02,818] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 138 +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +17: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +17: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,822] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 141 +28: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 137 +28: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +17: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +17: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:02,952] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 21 +17: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +28: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +17: [2022-11-24 17:06:02,837] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 140 +17: [2022-11-24 17:06:02,837] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 142 +28: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +17: [2022-11-24 17:06:02,837] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 143 +28: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +17: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,842] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +17: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,843] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 136 +28: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +17: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +17: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +17: [2022-11-24 17:06:02,849] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 139 +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +28: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,748] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,749] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +31: [2022-11-24 17:06:02,954] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 250 +28: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 227 +11: [2022-11-24 17:06:02,954] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 91 +28: [2022-11-24 17:06:02,805] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 231 +28: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt... +28: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +28: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,756] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,817] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +28: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +15: [2022-11-24 17:06:02,956] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 121 +28: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +28: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +28: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +28: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +28: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +28: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,773] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,777] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +28: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,839] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 228 +21: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:06:02,839] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 225 +21: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +28: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,841] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 230 +21: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +28: [2022-11-24 17:06:02,841] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 226 +21: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +28: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,846] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 229 +21: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +28: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +28: [2022-11-24 17:06:02,849] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 224 +21: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +28: [2022-11-24 17:06:02,941] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 227 +21: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_05-model_00-model_states.pt. +21: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,743] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +13: [2022-11-24 17:06:02,744] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,745] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,746] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +13: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,747] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,799] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,750] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,751] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,752] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt... +21: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,753] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 17:06:02,754] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 17:06:02,755] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,757] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,808] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_06-model_00-model_states.pt. +21: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,758] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,759] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,811] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,760] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,761] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,762] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,763] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +13: [2022-11-24 17:06:02,765] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,766] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,767] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt... +21: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,768] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... + 7: [2022-11-24 17:06:02,961] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 58 + 2: [2022-11-24 17:06:02,961] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 17 +21: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,769] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +13: [2022-11-24 17:06:02,770] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,771] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,821] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 170 +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_07-model_00-model_states.pt. +21: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,823] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 168 +21: [2022-11-24 17:06:02,823] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 169 +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,772] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,774] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,828] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,831] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,775] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,832] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,776] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,778] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,839] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt... +21: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,843] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,845] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,849] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,850] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_08-model_00-model_states.pt. +21: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,854] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +11: [2022-11-24 17:06:02,964] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +13: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +13: [2022-11-24 17:06:02,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,855] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,857] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,791] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,858] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,859] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +21: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +11: [2022-11-24 17:06:02,964] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 93 +21: [2022-11-24 17:06:02,861] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,862] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,863] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 171 +13: [2022-11-24 17:06:02,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +21: [2022-11-24 17:06:02,864] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,796] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,865] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,866] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 172 +13: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,866] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,867] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 174 +13: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt... +21: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,867] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,797] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,798] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,800] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +21: [2022-11-24 17:06:02,868] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +21: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:06:02,872] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,801] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,874] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +21: [2022-11-24 17:06:02,874] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 175 +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,874] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 173 +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,901] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 173 +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +21: [2022-11-24 17:06:02,903] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 175 +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +21: [2022-11-24 17:06:02,911] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 171 +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +21: [2022-11-24 17:06:02,928] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 172 +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,802] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +21: [2022-11-24 17:06:02,965] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 174 +13: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,803] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,804] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,805] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,807] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,807] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 109 +13: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,809] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,810] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,812] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,813] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,814] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,814] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 108 +13: [2022-11-24 17:06:02,815] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 109 +13: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,815] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,816] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,816] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 106 +13: [2022-11-24 17:06:02,816] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 110 +13: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +13: [2022-11-24 17:06:02,819] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,822] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,824] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,826] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,827] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... +13: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,829] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,830] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,833] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,834] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,835] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,836] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,837] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,838] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,840] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +13: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,841] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,841] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 111 +13: [2022-11-24 17:06:02,842] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 107 +13: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,844] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +13: [2022-11-24 17:06:02,844] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 105 +13: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,847] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +13: [2022-11-24 17:06:02,848] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +13: [2022-11-24 17:06:02,851] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:06:02,856] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:06:02,856] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 104 +13: [2022-11-24 17:06:02,866] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 108 + 3: [2022-11-24 17:06:02,969] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 30 + 3: [2022-11-24 17:06:02,970] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 28 +12: [2022-11-24 17:06:02,972] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 103 +25: [2022-11-24 17:06:02,973] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 207 +31: [2022-11-24 17:06:02,973] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 251 + 3: [2022-11-24 17:06:02,974] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 29 +13: [2022-11-24 17:06:02,977] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 110 +10: [2022-11-24 17:06:02,980] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 87 + 3: [2022-11-24 17:06:02,980] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 26 +10: [2022-11-24 17:06:02,980] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 86 + 3: [2022-11-24 17:06:02,980] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 27 +10: [2022-11-24 17:06:02,981] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 80 +10: [2022-11-24 17:06:02,982] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 83 +23: [2022-11-24 17:06:02,983] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_09-model_00-model_states.pt. +15: [2022-11-24 17:06:02,983] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 126 +20: [2022-11-24 17:06:02,983] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 165 +20: [2022-11-24 17:06:02,984] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 161 + 0: [2022-11-24 17:06:02,984] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 7 + 0: [2022-11-24 17:06:02,985] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 2 +20: [2022-11-24 17:06:02,985] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 164 +20: [2022-11-24 17:06:02,986] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 162 + 0: [2022-11-24 17:06:02,987] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 4 + 2: [2022-11-24 17:06:02,987] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 20 +20: [2022-11-24 17:06:02,988] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 163 + 9: [2022-11-24 17:06:02,988] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 77 + 6: [2022-11-24 17:06:02,989] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 53 +20: [2022-11-24 17:06:02,989] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 166 + 1: [2022-11-24 17:06:02,990] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 11 + 6: [2022-11-24 17:06:02,991] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 52 + 6: [2022-11-24 17:06:02,992] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 48 +11: [2022-11-24 17:06:02,995] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 95 +23: [2022-11-24 17:06:02,995] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 186 +24: [2022-11-24 17:06:03,001] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 199 + 9: [2022-11-24 17:06:03,001] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 76 +24: [2022-11-24 17:06:03,001] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 192 +16: [2022-11-24 17:06:03,007] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 134 +16: [2022-11-24 17:06:03,007] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 133 +28: [2022-11-24 17:06:03,009] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 229 +17: [2022-11-24 17:06:03,010] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 139 +19: [2022-11-24 17:06:03,013] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 157 +19: [2022-11-24 17:06:03,013] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 155 +19: [2022-11-24 17:06:03,014] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 154 +22: [2022-11-24 17:06:03,014] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 179 +30: [2022-11-24 17:06:03,015] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 241 +23: [2022-11-24 17:06:03,015] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 184 +16: [2022-11-24 17:06:03,017] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 135 +16: [2022-11-24 17:06:03,018] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 129 +21: [2022-11-24 17:06:03,018] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 170 +30: [2022-11-24 17:06:03,019] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 246 +22: [2022-11-24 17:06:03,021] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 183 +22: [2022-11-24 17:06:03,021] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 182 +27: [2022-11-24 17:06:03,023] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 219 + 3: [2022-11-24 17:06:03,024] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 31 +13: [2022-11-24 17:06:03,025] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 111 +19: [2022-11-24 17:06:03,025] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 159 +27: [2022-11-24 17:06:03,028] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 216 +27: [2022-11-24 17:06:03,028] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 220 +23: [2022-11-24 17:06:03,029] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... +13: [2022-11-24 17:06:03,030] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 106 + 4: [2022-11-24 17:06:03,031] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 35 + 7: [2022-11-24 17:06:03,032] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 57 +25: [2022-11-24 17:06:03,032] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 204 + 6: [2022-11-24 17:06:03,035] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 49 + 0: [2022-11-24 17:06:03,037] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 3 +26: [2022-11-24 17:06:03,037] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 215 +26: [2022-11-24 17:06:03,038] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 210 +13: [2022-11-24 17:06:03,038] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 107 +10: [2022-11-24 17:06:03,038] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 81 +10: [2022-11-24 17:06:03,039] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 82 +15: [2022-11-24 17:06:03,041] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 122 +13: [2022-11-24 17:06:03,042] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 105 +30: [2022-11-24 17:06:03,043] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 245 +30: [2022-11-24 17:06:03,044] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 240 + 7: [2022-11-24 17:06:03,045] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 62 +26: [2022-11-24 17:06:03,047] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 211 +13: [2022-11-24 17:06:03,051] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 104 +16: [2022-11-24 17:06:03,056] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 131 +12: [2022-11-24 17:06:03,063] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 100 +18: [2022-11-24 17:06:03,064] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 148 +18: [2022-11-24 17:06:03,068] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 149 +18: [2022-11-24 17:06:03,071] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 150 +17: [2022-11-24 17:06:03,071] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 138 +24: [2022-11-24 17:06:03,077] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 198 +24: [2022-11-24 17:06:03,078] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 197 +23: [2022-11-24 17:06:03,084] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. + 5: [2022-11-24 17:06:03,105] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 40 +12: [2022-11-24 17:06:03,127] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 102 +29: [2022-11-24 17:06:03,116] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 236 +23: [2022-11-24 17:06:03,084] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt... + 2: [2022-11-24 17:06:03,103] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 19 +15: [2022-11-24 17:06:03,114] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 125 +27: [2022-11-24 17:06:03,094] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 217 + 8: [2022-11-24 17:06:03,094] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 64 +28: [2022-11-24 17:06:03,088] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 224 + 5: [2022-11-24 17:06:03,107] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 46 +23: [2022-11-24 17:06:03,102] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 185 +27: [2022-11-24 17:06:03,095] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 222 +28: [2022-11-24 17:06:03,089] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 225 +12: [2022-11-24 17:06:03,128] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 97 +29: [2022-11-24 17:06:03,117] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 232 + 2: [2022-11-24 17:06:03,114] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 18 +28: [2022-11-24 17:06:03,091] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 228 +29: [2022-11-24 17:06:03,119] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 234 + 2: [2022-11-24 17:06:03,127] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 22 +28: [2022-11-24 17:06:03,095] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 226 +29: [2022-11-24 17:06:03,128] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 239 +29: [2022-11-24 17:06:03,129] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 238 +29: [2022-11-24 17:06:03,133] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 233 + 0: [2022-11-24 17:06:03,138] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 1 +23: [2022-11-24 17:06:03,142] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_10-model_00-model_states.pt. +28: [2022-11-24 17:06:03,144] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 230 +23: [2022-11-24 17:06:03,145] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 4: [2022-11-24 17:06:03,147] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 33 + 4: [2022-11-24 17:06:03,148] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 32 +11: [2022-11-24 17:06:03,155] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 89 +11: [2022-11-24 17:06:03,186] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 93 +24: [2022-11-24 17:06:03,190] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 193 + 9: [2022-11-24 17:06:03,199] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 73 +23: [2022-11-24 17:06:03,203] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:03,203] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:06:03,205] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 6 +28: [2022-11-24 17:06:03,207] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 231 +23: [2022-11-24 17:06:03,211] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_11-model_00-model_states.pt. +23: [2022-11-24 17:06:03,214] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +16: [2022-11-24 17:06:03,216] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 130 +16: [2022-11-24 17:06:03,217] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 128 +23: [2022-11-24 17:06:03,223] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:03,223] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt... +19: [2022-11-24 17:06:03,224] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 152 +19: [2022-11-24 17:06:03,226] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 153 +19: [2022-11-24 17:06:03,226] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 156 +17: [2022-11-24 17:06:03,230] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 137 +23: [2022-11-24 17:06:03,231] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_12-model_00-model_states.pt. +23: [2022-11-24 17:06:03,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:03,234] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +23: [2022-11-24 17:06:03,234] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt... +23: [2022-11-24 17:06:03,235] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/layer_14-model_00-model_states.pt. +24: [2022-11-24 17:06:03,236] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 194 +21: [2022-11-24 17:06:03,238] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 169 +23: [2022-11-24 17:06:03,238] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:06:03,244] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_83m/global_step36000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:06:03,244] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 256 ZeRO state_dicts for rank 191 + 6: [2022-11-24 17:06:03,245] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 55 +21: [2022-11-24 17:06:03,268] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 168 +23: [2022-11-24 17:06:03,272] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 191 +18: [2022-11-24 17:06:03,277] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 145 +19: [2022-11-24 17:06:03,285] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 158 +17: [2022-11-24 17:06:03,285] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 142 +18: [2022-11-24 17:06:03,311] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 151 +17: [2022-11-24 17:06:03,324] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 141 +17: [2022-11-24 17:06:03,357] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 143 +17: [2022-11-24 17:06:03,358] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 256 zero partition checkpoints for rank 140 + 0: successfully loaded checkpoint from checkpoints_83m at iteration 36000 +31: time (ms) | load-checkpoint: 788.67 + 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: 2022-11-24 17:06:04 + 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 0.001445 seconds + 0: number of documents: 210604984 + 0: > dataset split: + 0: train: + 0: document indices in [0, 199864130) total of 199864130 documents + 0: validation: + 0: document indices in [199864130, 210394379) total of 10530249 documents + 0: test: + 0: document indices in [210394379, 210604984) total of 210605 documents + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_train_indexmap_9703701ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.005 seconds + 0: total number of samples: 173377817 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_valid_indexmap_9728ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.004 seconds + 0: total number of samples: 9118345 + 0: total number of epochs: 1 + 0: > loading doc-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_doc_idx.npy + 0: > loading sample-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_sample_idx.npy + 0: > loading shuffle-idx mapping from /scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document_test_indexmap_256ns_2048sl_1234s_shuffle_idx.npy + 0: loaded indexed file in 0.003 seconds + 0: total number of samples: 182928 + 0: total number of epochs: 1 + 0: > finished creating GPT datasets ... + 0: [after dataloaders are built] datetime: 2022-11-24 17:06:26 + 0: done with setup ... + 0: training ... + 0: Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +31: time (ms) | model-and-optimizer-setup: 28597.99 | train/valid/test-data-iterators-setup: 21273.11 + 0: [000-000] 0.0827B / 0.0492B + 0: [before the start of training step] datetime: 2022-11-24 17:06:26 + 0: [2022-11-24 17:06:26,829] [INFO] [checkpointing.py:553:forward] Activation Checkpointing Information + 0: [2022-11-24 17:06:26,830] [INFO] [checkpointing.py:554:forward] ----Partition Activations False, CPU CHECKPOINTING False + 0: [2022-11-24 17:06:26,830] [INFO] [checkpointing.py:557:forward] ----contiguous Memory Checkpointing False with None total layers + 0: [2022-11-24 17:06:26,830] [INFO] [checkpointing.py:560:forward] ----Synchronization False + 0: [2022-11-24 17:06:26,830] [INFO] [checkpointing.py:561:forward] ----Profiling time in checkpointing False + 0: [Rank 0] (after 36010 iterations) memory (MB) | allocated: 1042.54638671875 | max allocated: 1703.8681640625 | reserved: 2544.0 | max reserved: 2544.0 +31: iteration 36010/ 37905 | consumed samples: 9218560 | consumed tokens: 18879610880 | elapsed time per iteration (s): 1.13 | learning rate: 2.111E-05 | global batch size: 256 | lm loss: 2.875034E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 227.502 | TFLOPs: 1.45 | +31: iteration 36020/ 37905 | consumed samples: 9221120 | consumed tokens: 18884853760 | elapsed time per iteration (s): 0.22 | learning rate: 2.110E-05 | global batch size: 256 | lm loss: 2.886648E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1183.794 | TFLOPs: 7.54 | +31: iteration 36030/ 37905 | consumed samples: 9223680 | consumed tokens: 18890096640 | elapsed time per iteration (s): 0.22 | learning rate: 2.108E-05 | global batch size: 256 | lm loss: 2.865829E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1156.433 | TFLOPs: 7.37 | +31: iteration 36040/ 37905 | consumed samples: 9226240 | consumed tokens: 18895339520 | elapsed time per iteration (s): 0.23 | learning rate: 2.107E-05 | global batch size: 256 | lm loss: 2.881052E+00 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1103.036 | TFLOPs: 7.03 | +31: iteration 36050/ 37905 | consumed samples: 9228800 | consumed tokens: 18900582400 | elapsed time per iteration (s): 0.30 | learning rate: 2.106E-05 | global batch size: 256 | lm loss: 2.905450E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 842.087 | TFLOPs: 5.36 | +31: iteration 36060/ 37905 | consumed samples: 9231360 | consumed tokens: 18905825280 | elapsed time per iteration (s): 0.28 | learning rate: 2.105E-05 | global batch size: 256 | lm loss: 2.913760E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 919.798 | TFLOPs: 5.86 | +31: iteration 36070/ 37905 | consumed samples: 9233920 | consumed tokens: 18911068160 | elapsed time per iteration (s): 0.31 | learning rate: 2.104E-05 | global batch size: 256 | lm loss: 2.899444E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 822.160 | TFLOPs: 5.24 | +31: iteration 36080/ 37905 | consumed samples: 9236480 | consumed tokens: 18916311040 | elapsed time per iteration (s): 0.25 | learning rate: 2.103E-05 | global batch size: 256 | lm loss: 2.876626E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1007.094 | TFLOPs: 6.41 | +31: iteration 36090/ 37905 | consumed samples: 9239040 | consumed tokens: 18921553920 | elapsed time per iteration (s): 0.25 | learning rate: 2.102E-05 | global batch size: 256 | lm loss: 2.869850E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1026.997 | TFLOPs: 6.54 | +31: iteration 36100/ 37905 | consumed samples: 9241600 | consumed tokens: 18926796800 | elapsed time per iteration (s): 0.26 | learning rate: 2.101E-05 | global batch size: 256 | lm loss: 2.925788E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 989.948 | TFLOPs: 6.30 | +31: iteration 36110/ 37905 | consumed samples: 9244160 | consumed tokens: 18932039680 | elapsed time per iteration (s): 0.30 | learning rate: 2.099E-05 | global batch size: 256 | lm loss: 2.901951E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 865.712 | TFLOPs: 5.51 | +31: iteration 36120/ 37905 | consumed samples: 9246720 | consumed tokens: 18937282560 | elapsed time per iteration (s): 0.24 | learning rate: 2.098E-05 | global batch size: 256 | lm loss: 2.886228E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.010 | TFLOPs: 6.72 | +31: iteration 36130/ 37905 | consumed samples: 9249280 | consumed tokens: 18942525440 | elapsed time per iteration (s): 0.21 | learning rate: 2.097E-05 | global batch size: 256 | lm loss: 2.864394E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1191.977 | TFLOPs: 7.59 | +31: iteration 36140/ 37905 | consumed samples: 9251840 | consumed tokens: 18947768320 | elapsed time per iteration (s): 0.22 | learning rate: 2.096E-05 | global batch size: 256 | lm loss: 2.870307E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.676 | TFLOPs: 7.30 | +31: iteration 36150/ 37905 | consumed samples: 9254400 | consumed tokens: 18953011200 | elapsed time per iteration (s): 0.24 | learning rate: 2.095E-05 | global batch size: 256 | lm loss: 2.926268E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.585 | TFLOPs: 6.75 | +31: iteration 36160/ 37905 | consumed samples: 9256960 | consumed tokens: 18958254080 | elapsed time per iteration (s): 0.29 | learning rate: 2.094E-05 | global batch size: 256 | lm loss: 2.925979E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 877.367 | TFLOPs: 5.59 | +31: iteration 36170/ 37905 | consumed samples: 9259520 | consumed tokens: 18963496960 | elapsed time per iteration (s): 0.26 | learning rate: 2.093E-05 | global batch size: 256 | lm loss: 2.908002E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.455 | TFLOPs: 6.31 | +31: iteration 36180/ 37905 | consumed samples: 9262080 | consumed tokens: 18968739840 | elapsed time per iteration (s): 0.24 | learning rate: 2.092E-05 | global batch size: 256 | lm loss: 2.891486E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.741 | TFLOPs: 6.76 | +31: iteration 36190/ 37905 | consumed samples: 9264640 | consumed tokens: 18973982720 | elapsed time per iteration (s): 0.28 | learning rate: 2.091E-05 | global batch size: 256 | lm loss: 2.885267E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 910.763 | TFLOPs: 5.80 | +31: iteration 36200/ 37905 | consumed samples: 9267200 | consumed tokens: 18979225600 | elapsed time per iteration (s): 0.23 | learning rate: 2.090E-05 | global batch size: 256 | lm loss: 2.914770E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1131.859 | TFLOPs: 7.21 | +31: iteration 36210/ 37905 | consumed samples: 9269760 | consumed tokens: 18984468480 | elapsed time per iteration (s): 0.25 | learning rate: 2.089E-05 | global batch size: 256 | lm loss: 2.879210E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.116 | TFLOPs: 6.61 | +31: iteration 36220/ 37905 | consumed samples: 9272320 | consumed tokens: 18989711360 | elapsed time per iteration (s): 0.22 | learning rate: 2.088E-05 | global batch size: 256 | lm loss: 2.916792E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1168.566 | TFLOPs: 7.44 | +31: iteration 36230/ 37905 | consumed samples: 9274880 | consumed tokens: 18994954240 | elapsed time per iteration (s): 0.21 | learning rate: 2.087E-05 | global batch size: 256 | lm loss: 2.907865E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1217.897 | TFLOPs: 7.76 | +31: iteration 36240/ 37905 | consumed samples: 9277440 | consumed tokens: 19000197120 | elapsed time per iteration (s): 0.23 | learning rate: 2.086E-05 | global batch size: 256 | lm loss: 2.906250E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.036 | TFLOPs: 7.08 | +31: iteration 36250/ 37905 | consumed samples: 9280000 | consumed tokens: 19005440000 | elapsed time per iteration (s): 0.30 | learning rate: 2.085E-05 | global batch size: 256 | lm loss: 2.873895E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 839.966 | TFLOPs: 5.35 | +31: iteration 36260/ 37905 | consumed samples: 9282560 | consumed tokens: 19010682880 | elapsed time per iteration (s): 0.21 | learning rate: 2.084E-05 | global batch size: 256 | lm loss: 2.863333E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1221.544 | TFLOPs: 7.78 | +31: iteration 36270/ 37905 | consumed samples: 9285120 | consumed tokens: 19015925760 | elapsed time per iteration (s): 0.22 | learning rate: 2.083E-05 | global batch size: 256 | lm loss: 2.908844E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1146.904 | TFLOPs: 7.30 | +31: iteration 36280/ 37905 | consumed samples: 9287680 | consumed tokens: 19021168640 | elapsed time per iteration (s): 0.20 | learning rate: 2.082E-05 | global batch size: 256 | lm loss: 2.878504E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1292.360 | TFLOPs: 8.23 | +31: iteration 36290/ 37905 | consumed samples: 9290240 | consumed tokens: 19026411520 | elapsed time per iteration (s): 0.23 | learning rate: 2.081E-05 | global batch size: 256 | lm loss: 2.909422E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.660 | TFLOPs: 7.15 | +31: iteration 36300/ 37905 | consumed samples: 9292800 | consumed tokens: 19031654400 | elapsed time per iteration (s): 0.19 | learning rate: 2.080E-05 | global batch size: 256 | lm loss: 2.912795E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1367.999 | TFLOPs: 8.71 | +31: iteration 36310/ 37905 | consumed samples: 9295360 | consumed tokens: 19036897280 | elapsed time per iteration (s): 0.20 | learning rate: 2.079E-05 | global batch size: 256 | lm loss: 2.908192E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1277.109 | TFLOPs: 8.13 | +31: iteration 36320/ 37905 | consumed samples: 9297920 | consumed tokens: 19042140160 | elapsed time per iteration (s): 0.19 | learning rate: 2.078E-05 | global batch size: 256 | lm loss: 2.877349E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1360.378 | TFLOPs: 8.66 | +31: iteration 36330/ 37905 | consumed samples: 9300480 | consumed tokens: 19047383040 | elapsed time per iteration (s): 0.18 | learning rate: 2.077E-05 | global batch size: 256 | lm loss: 2.855331E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1409.661 | TFLOPs: 8.98 | +31: iteration 36340/ 37905 | consumed samples: 9303040 | consumed tokens: 19052625920 | elapsed time per iteration (s): 0.19 | learning rate: 2.076E-05 | global batch size: 256 | lm loss: 2.895671E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.992 | TFLOPs: 8.42 | +31: iteration 36350/ 37905 | consumed samples: 9305600 | consumed tokens: 19057868800 | elapsed time per iteration (s): 0.19 | learning rate: 2.075E-05 | global batch size: 256 | lm loss: 2.861573E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1332.339 | TFLOPs: 8.49 | +31: iteration 36360/ 37905 | consumed samples: 9308160 | consumed tokens: 19063111680 | elapsed time per iteration (s): 0.21 | learning rate: 2.074E-05 | global batch size: 256 | lm loss: 2.903195E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.169 | TFLOPs: 7.93 | +31: iteration 36370/ 37905 | consumed samples: 9310720 | consumed tokens: 19068354560 | elapsed time per iteration (s): 0.19 | learning rate: 2.073E-05 | global batch size: 256 | lm loss: 2.890572E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1351.750 | TFLOPs: 8.61 | +31: iteration 36380/ 37905 | consumed samples: 9313280 | consumed tokens: 19073597440 | elapsed time per iteration (s): 0.19 | learning rate: 2.072E-05 | global batch size: 256 | lm loss: 2.911003E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.164 | TFLOPs: 8.58 | +31: iteration 36390/ 37905 | consumed samples: 9315840 | consumed tokens: 19078840320 | elapsed time per iteration (s): 0.20 | learning rate: 2.071E-05 | global batch size: 256 | lm loss: 2.882359E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1272.122 | TFLOPs: 8.10 | +31: iteration 36400/ 37905 | consumed samples: 9318400 | consumed tokens: 19084083200 | elapsed time per iteration (s): 0.20 | learning rate: 2.070E-05 | global batch size: 256 | lm loss: 2.912443E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1251.648 | TFLOPs: 7.97 | +31: iteration 36410/ 37905 | consumed samples: 9320960 | consumed tokens: 19089326080 | elapsed time per iteration (s): 0.19 | learning rate: 2.069E-05 | global batch size: 256 | lm loss: 2.871431E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.396 | TFLOPs: 8.42 | +31: iteration 36420/ 37905 | consumed samples: 9323520 | consumed tokens: 19094568960 | elapsed time per iteration (s): 0.18 | learning rate: 2.068E-05 | global batch size: 256 | lm loss: 2.874770E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1439.613 | TFLOPs: 9.17 | +31: iteration 36430/ 37905 | consumed samples: 9326080 | consumed tokens: 19099811840 | elapsed time per iteration (s): 0.19 | learning rate: 2.067E-05 | global batch size: 256 | lm loss: 2.890210E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1369.065 | TFLOPs: 8.72 | +31: iteration 36440/ 37905 | consumed samples: 9328640 | consumed tokens: 19105054720 | elapsed time per iteration (s): 0.22 | learning rate: 2.066E-05 | global batch size: 256 | lm loss: 2.869658E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1145.108 | TFLOPs: 7.29 | +31: iteration 36450/ 37905 | consumed samples: 9331200 | consumed tokens: 19110297600 | elapsed time per iteration (s): 0.23 | learning rate: 2.065E-05 | global batch size: 256 | lm loss: 2.908603E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1126.942 | TFLOPs: 7.18 | +31: iteration 36460/ 37905 | consumed samples: 9333760 | consumed tokens: 19115540480 | elapsed time per iteration (s): 0.21 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 2.884865E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1246.050 | TFLOPs: 7.94 | +31: iteration 36470/ 37905 | consumed samples: 9336320 | consumed tokens: 19120783360 | elapsed time per iteration (s): 0.20 | learning rate: 2.064E-05 | global batch size: 256 | lm loss: 2.872897E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1289.569 | TFLOPs: 8.21 | +31: iteration 36480/ 37905 | consumed samples: 9338880 | consumed tokens: 19126026240 | elapsed time per iteration (s): 0.19 | learning rate: 2.063E-05 | global batch size: 256 | lm loss: 2.898441E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1326.955 | TFLOPs: 8.45 | +31: iteration 36490/ 37905 | consumed samples: 9341440 | consumed tokens: 19131269120 | elapsed time per iteration (s): 0.19 | learning rate: 2.062E-05 | global batch size: 256 | lm loss: 2.908790E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1359.530 | TFLOPs: 8.66 | +31: iteration 36500/ 37905 | consumed samples: 9344000 | consumed tokens: 19136512000 | elapsed time per iteration (s): 0.19 | learning rate: 2.061E-05 | global batch size: 256 | lm loss: 2.859162E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1365.318 | TFLOPs: 8.70 | +31: iteration 36510/ 37905 | consumed samples: 9346560 | consumed tokens: 19141754880 | elapsed time per iteration (s): 0.19 | learning rate: 2.060E-05 | global batch size: 256 | lm loss: 2.901369E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1358.146 | TFLOPs: 8.65 | +31: iteration 36520/ 37905 | consumed samples: 9349120 | consumed tokens: 19146997760 | elapsed time per iteration (s): 0.20 | learning rate: 2.059E-05 | global batch size: 256 | lm loss: 2.859150E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1256.662 | TFLOPs: 8.00 | +31: iteration 36530/ 37905 | consumed samples: 9351680 | consumed tokens: 19152240640 | elapsed time per iteration (s): 0.19 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.892040E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1369.588 | TFLOPs: 8.72 | +31: iteration 36540/ 37905 | consumed samples: 9354240 | consumed tokens: 19157483520 | elapsed time per iteration (s): 0.19 | learning rate: 2.058E-05 | global batch size: 256 | lm loss: 2.892833E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1336.422 | TFLOPs: 8.51 | +31: iteration 36550/ 37905 | consumed samples: 9356800 | consumed tokens: 19162726400 | elapsed time per iteration (s): 0.20 | learning rate: 2.057E-05 | global batch size: 256 | lm loss: 2.890966E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1280.684 | TFLOPs: 8.16 | +31: iteration 36560/ 37905 | consumed samples: 9359360 | consumed tokens: 19167969280 | elapsed time per iteration (s): 0.18 | learning rate: 2.056E-05 | global batch size: 256 | lm loss: 2.902261E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1384.632 | TFLOPs: 8.82 | +31: iteration 36570/ 37905 | consumed samples: 9361920 | consumed tokens: 19173212160 | elapsed time per iteration (s): 0.19 | learning rate: 2.055E-05 | global batch size: 256 | lm loss: 2.873650E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1350.440 | TFLOPs: 8.60 | +31: iteration 36580/ 37905 | consumed samples: 9364480 | consumed tokens: 19178455040 | elapsed time per iteration (s): 0.19 | learning rate: 2.054E-05 | global batch size: 256 | lm loss: 2.861152E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1360.166 | TFLOPs: 8.66 | +31: iteration 36590/ 37905 | consumed samples: 9367040 | consumed tokens: 19183697920 | elapsed time per iteration (s): 0.19 | learning rate: 2.053E-05 | global batch size: 256 | lm loss: 2.879736E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1356.293 | TFLOPs: 8.64 | +31: iteration 36600/ 37905 | consumed samples: 9369600 | consumed tokens: 19188940800 | elapsed time per iteration (s): 0.19 | learning rate: 2.053E-05 | global batch size: 256 | lm loss: 2.841673E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1317.084 | TFLOPs: 8.39 | +31: iteration 36610/ 37905 | consumed samples: 9372160 | consumed tokens: 19194183680 | elapsed time per iteration (s): 0.19 | learning rate: 2.052E-05 | global batch size: 256 | lm loss: 2.921107E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1347.097 | TFLOPs: 8.58 | +31: iteration 36620/ 37905 | consumed samples: 9374720 | consumed tokens: 19199426560 | elapsed time per iteration (s): 0.18 | learning rate: 2.051E-05 | global batch size: 256 | lm loss: 2.891282E+00 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1397.380 | TFLOPs: 8.90 | +31: iteration 36630/ 37905 | consumed samples: 9377280 | consumed tokens: 19204669440 | elapsed time per iteration (s): 0.20 | learning rate: 2.050E-05 | global batch size: 256 | lm loss: 2.837898E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1305.183 | TFLOPs: 8.31 | +31: iteration 36640/ 37905 | consumed samples: 9379840 | consumed tokens: 19209912320 | elapsed time per iteration (s): 0.18 | learning rate: 2.049E-05 | global batch size: 256 | lm loss: 2.883154E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1413.042 | TFLOPs: 9.00 | +31: iteration 36650/ 37905 | consumed samples: 9382400 | consumed tokens: 19215155200 | elapsed time per iteration (s): 0.19 | learning rate: 2.049E-05 | global batch size: 256 | lm loss: 2.869710E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1353.578 | TFLOPs: 8.62 | +31: iteration 36660/ 37905 | consumed samples: 9384960 | consumed tokens: 19220398080 | elapsed time per iteration (s): 0.19 | learning rate: 2.048E-05 | global batch size: 256 | lm loss: 2.890990E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1313.808 | TFLOPs: 8.37 | +31: iteration 36670/ 37905 | consumed samples: 9387520 | consumed tokens: 19225640960 | elapsed time per iteration (s): 0.22 | learning rate: 2.047E-05 | global batch size: 256 | lm loss: 2.905231E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1182.158 | TFLOPs: 7.53 | +31: iteration 36680/ 37905 | consumed samples: 9390080 | consumed tokens: 19230883840 | elapsed time per iteration (s): 0.20 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.890004E+00 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1279.816 | TFLOPs: 8.15 | +31: iteration 36690/ 37905 | consumed samples: 9392640 | consumed tokens: 19236126720 | elapsed time per iteration (s): 0.21 | learning rate: 2.046E-05 | global batch size: 256 | lm loss: 2.886239E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1245.270 | TFLOPs: 7.93 | +31: iteration 36700/ 37905 | consumed samples: 9395200 | consumed tokens: 19241369600 | elapsed time per iteration (s): 0.19 | learning rate: 2.045E-05 | global batch size: 256 | lm loss: 2.884292E+00 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1330.523 | TFLOPs: 8.47 | +31: iteration 36710/ 37905 | consumed samples: 9397760 | consumed tokens: 19246612480 | elapsed time per iteration (s): 0.19 | learning rate: 2.044E-05 | global batch size: 256 | lm loss: 2.872428E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1315.466 | TFLOPs: 8.38 | +31: iteration 36720/ 37905 | consumed samples: 9400320 | consumed tokens: 19251855360 | elapsed time per iteration (s): 0.18 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 2.869320E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1390.349 | TFLOPs: 8.85 | +31: iteration 36730/ 37905 | consumed samples: 9402880 | consumed tokens: 19257098240 | elapsed time per iteration (s): 0.18 | learning rate: 2.043E-05 | global batch size: 256 | lm loss: 2.892738E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.523 | TFLOPs: 8.93 | +31: iteration 36740/ 37905 | consumed samples: 9405440 | consumed tokens: 19262341120 | elapsed time per iteration (s): 0.18 | learning rate: 2.042E-05 | global batch size: 256 | lm loss: 2.901523E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1402.434 | TFLOPs: 8.93 | +31: iteration 36750/ 37905 | consumed samples: 9408000 | consumed tokens: 19267584000 | elapsed time per iteration (s): 0.18 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 2.876865E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1422.311 | TFLOPs: 9.06 | +31: iteration 36760/ 37905 | consumed samples: 9410560 | consumed tokens: 19272826880 | elapsed time per iteration (s): 0.20 | learning rate: 2.041E-05 | global batch size: 256 | lm loss: 2.895394E+00 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1307.389 | TFLOPs: 8.33 | +31: iteration 36770/ 37905 | consumed samples: 9413120 | consumed tokens: 19278069760 | elapsed time per iteration (s): 0.19 | learning rate: 2.040E-05 | global batch size: 256 | lm loss: 2.878531E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1340.737 | TFLOPs: 8.54 | +31: iteration 36780/ 37905 | consumed samples: 9415680 | consumed tokens: 19283312640 | elapsed time per iteration (s): 0.18 | learning rate: 2.039E-05 | global batch size: 256 | lm loss: 2.917804E+00 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1431.500 | TFLOPs: 9.12 | +31: iteration 36790/ 37905 | consumed samples: 9418240 | consumed tokens: 19288555520 | elapsed time per iteration (s): 0.20 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.904743E+00 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1290.449 | TFLOPs: 8.22 | +31: iteration 36800/ 37905 | consumed samples: 9420800 | consumed tokens: 19293798400 | elapsed time per iteration (s): 0.18 | learning rate: 2.038E-05 | global batch size: 256 | lm loss: 2.870599E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1454.534 | TFLOPs: 9.26 | +31: iteration 36810/ 37905 | consumed samples: 9423360 | consumed tokens: 19299041280 | elapsed time per iteration (s): 0.20 | learning rate: 2.037E-05 | global batch size: 256 | lm loss: 2.895813E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1302.421 | TFLOPs: 8.29 | +31: iteration 36820/ 37905 | consumed samples: 9425920 | consumed tokens: 19304284160 | elapsed time per iteration (s): 0.18 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.901664E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1392.883 | TFLOPs: 8.87 | +31: iteration 36830/ 37905 | consumed samples: 9428480 | consumed tokens: 19309527040 | elapsed time per iteration (s): 0.19 | learning rate: 2.036E-05 | global batch size: 256 | lm loss: 2.899883E+00 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1380.356 | TFLOPs: 8.79 | +31: iteration 36840/ 37905 | consumed samples: 9431040 | consumed tokens: 19314769920 | elapsed time per iteration (s): 0.21 | learning rate: 2.035E-05 | global batch size: 256 | lm loss: 2.873335E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1207.281 | TFLOPs: 7.69 | +31: iteration 36850/ 37905 | consumed samples: 9433600 | consumed tokens: 19320012800 | elapsed time per iteration (s): 0.18 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.909697E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1419.896 | TFLOPs: 9.04 | +31: iteration 36860/ 37905 | consumed samples: 9436160 | consumed tokens: 19325255680 | elapsed time per iteration (s): 0.19 | learning rate: 2.034E-05 | global batch size: 256 | lm loss: 2.896464E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1383.513 | TFLOPs: 8.81 | +31: iteration 36870/ 37905 | consumed samples: 9438720 | consumed tokens: 19330498560 | elapsed time per iteration (s): 0.20 | learning rate: 2.033E-05 | global batch size: 256 | lm loss: 2.861786E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1259.062 | TFLOPs: 8.02 | +31: iteration 36880/ 37905 | consumed samples: 9441280 | consumed tokens: 19335741440 | elapsed time per iteration (s): 0.18 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.854629E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1438.264 | TFLOPs: 9.16 | +31: iteration 36890/ 37905 | consumed samples: 9443840 | consumed tokens: 19340984320 | elapsed time per iteration (s): 0.18 | learning rate: 2.032E-05 | global batch size: 256 | lm loss: 2.875157E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1403.619 | TFLOPs: 8.94 | +31: iteration 36900/ 37905 | consumed samples: 9446400 | consumed tokens: 19346227200 | elapsed time per iteration (s): 0.19 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.921170E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1346.945 | TFLOPs: 8.58 | +31: iteration 36910/ 37905 | consumed samples: 9448960 | consumed tokens: 19351470080 | elapsed time per iteration (s): 0.18 | learning rate: 2.031E-05 | global batch size: 256 | lm loss: 2.924317E+00 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1423.314 | TFLOPs: 9.06 | +31: iteration 36920/ 37905 | consumed samples: 9451520 | consumed tokens: 19356712960 | elapsed time per iteration (s): 0.20 | learning rate: 2.030E-05 | global batch size: 256 | lm loss: 2.893167E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1269.729 | TFLOPs: 8.09 | +31: iteration 36930/ 37905 | consumed samples: 9454080 | consumed tokens: 19361955840 | elapsed time per iteration (s): 0.19 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.908124E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1382.666 | TFLOPs: 8.81 | +31: iteration 36940/ 37905 | consumed samples: 9456640 | consumed tokens: 19367198720 | elapsed time per iteration (s): 0.19 | learning rate: 2.029E-05 | global batch size: 256 | lm loss: 2.926399E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1354.013 | TFLOPs: 8.62 | +31: iteration 36950/ 37905 | consumed samples: 9459200 | consumed tokens: 19372441600 | elapsed time per iteration (s): 0.19 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.885104E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1323.865 | TFLOPs: 8.43 | +31: iteration 36960/ 37905 | consumed samples: 9461760 | consumed tokens: 19377684480 | elapsed time per iteration (s): 0.18 | learning rate: 2.028E-05 | global batch size: 256 | lm loss: 2.866648E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1407.151 | TFLOPs: 8.96 | +31: iteration 36970/ 37905 | consumed samples: 9464320 | consumed tokens: 19382927360 | elapsed time per iteration (s): 0.19 | learning rate: 2.027E-05 | global batch size: 256 | lm loss: 2.908297E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1364.717 | TFLOPs: 8.69 | +31: iteration 36980/ 37905 | consumed samples: 9466880 | consumed tokens: 19388170240 | elapsed time per iteration (s): 0.18 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.902516E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1385.900 | TFLOPs: 8.83 | +31: iteration 36990/ 37905 | consumed samples: 9469440 | consumed tokens: 19393413120 | elapsed time per iteration (s): 0.19 | learning rate: 2.026E-05 | global batch size: 256 | lm loss: 2.872168E+00 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1321.558 | TFLOPs: 8.42 | +31: iteration 37000/ 37905 | consumed samples: 9472000 | consumed tokens: 19398656000 | elapsed time per iteration (s): 0.18 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 2.880073E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1392.667 | TFLOPs: 8.87 | +31: ------------------------------------------------------------------------------------------- +31: valid loss at iteration 37000 | lm loss value: 2.859078E+00 | lm loss PPL: 1.744544E+01 | +31: ------------------------------------------------------------------------------------------- + 0: saving checkpoint at iteration 37000 to checkpoints_83m + 0: [2022-11-24 17:10:03,373] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step37000 is begin to save! + 0: [2022-11-24 17:10:03,606] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,733] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,744] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,745] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,756] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,767] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,767] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,778] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,800] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,800] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,811] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,811] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,834] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,834] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:10:03,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:10:03,836] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step37000/mp_rank_00_model_states.pt + 0: [2022-11-24 17:10:03,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:10:03,838] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:10:03,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:10:04,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,004] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,004] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:10:04,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:10:04,005] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,005] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: [2022-11-24 17:10:04,005] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +16: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:10:04,006] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,006] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +11: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +28: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +20: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,007] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 17:10:04,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:10:04,008] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,008] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +12: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +19: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +13: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,009] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,009] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +17: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,010] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,010] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,010] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +16: [2022-11-24 17:10:04,010] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:10:04,010] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,010] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +15: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +25: [2022-11-24 17:10:04,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt +28: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +15: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +11: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,011] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: [2022-11-24 17:10:04,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:10:04,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:10:04,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,012] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,012] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,012] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:10:04,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 5: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +19: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:10:04,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,013] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:10:04,013] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +13: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:10:04,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +20: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt +31: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:10:04,014] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +30: [2022-11-24 17:10:04,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,015] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,015] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:10:04,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +12: [2022-11-24 17:10:04,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +17: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,016] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,016] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +16: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,017] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,017] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:10:04,017] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,018] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt +25: [2022-11-24 17:10:04,017] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +28: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,018] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +15: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,018] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:10:04,018] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +11: [2022-11-24 17:10:04,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,018] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,019] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: [2022-11-24 17:10:04,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,019] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:10:04,019] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,019] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +19: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +13: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:10:04,020] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,020] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:10:04,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:10:04,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +31: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +20: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +20: [2022-11-24 17:10:04,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:10:04,021] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,021] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,022] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,022] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,022] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,022] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +12: [2022-11-24 17:10:04,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,022] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,022] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,022] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:10:04,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +17: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:10:04,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,023] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:10:04,023] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +16: [2022-11-24 17:10:04,024] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +15: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +28: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +28: [2022-11-24 17:10:04,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +28: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +11: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,025] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: [2022-11-24 17:10:04,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:10:04,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:10:04,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,026] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:10:04,026] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,026] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +19: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:10:04,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 5: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +13: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:10:04,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:10:04,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,027] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt +31: [2022-11-24 17:10:04,027] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +30: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:10:04,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 2: [2022-11-24 17:10:04,028] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,028] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt +10: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +18: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +18: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,029] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +10: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,030] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,030] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:10:04,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +16: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt +25: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +15: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,031] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +28: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:10:04,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +11: [2022-11-24 17:10:04,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,032] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +18: [2022-11-24 17:10:04,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:10:04,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +19: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,033] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,033] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:10:04,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 5: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:10:04,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +13: [2022-11-24 17:10:04,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +20: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:10:04,034] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt +30: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 2: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,035] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,035] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +12: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:10:04,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:10:04,036] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +17: [2022-11-24 17:10:04,036] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:10:04,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:10:04,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,037] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:10:04,037] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,037] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:10:04,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +15: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +11: [2022-11-24 17:10:04,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,038] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +28: [2022-11-24 17:10:04,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +28: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:10:04,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,039] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +18: [2022-11-24 17:10:04,039] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:10:04,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +19: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 5: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,040] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,040] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:10:04,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +13: [2022-11-24 17:10:04,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +20: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,041] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:10:04,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 2: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:10:04,042] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +12: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:10:04,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,043] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +17: [2022-11-24 17:10:04,043] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:10:04,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:10:04,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +16: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,044] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +15: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +11: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,045] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +11: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +28: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:10:04,045] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +28: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,046] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +18: [2022-11-24 17:10:04,046] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:10:04,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +19: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:10:04,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 5: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,047] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,047] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:10:04,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +13: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:10:04,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:10:04,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +31: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +20: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,048] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,048] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +10: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 6: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +15: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +30: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 3: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +27: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +22: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 5: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +31: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +20: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +10: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +25: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +30: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +17: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 7: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +12: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +29: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +23: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +26: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +14: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +19: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 2: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +27: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +24: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt +16: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +18: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +25: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +30: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,049] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +12: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +29: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +23: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +26: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +31: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +14: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 1: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 2: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +22: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +10: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 4: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 8: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +16: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 9: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +17: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt +21: [2022-11-24 17:10:04,050] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37000/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt +13: [2022-11-24 17:10:04,049] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +24: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +17: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! +21: [2022-11-24 17:10:04,050] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37000 is ready now! + 0: successfully saved checkpoint at iteration 37000 to checkpoints_83m +31: time (ms) | save-checkpoint: 683.16 +31: iteration 37010/ 37905 | consumed samples: 9474560 | consumed tokens: 19403898880 | elapsed time per iteration (s): 0.32 | learning rate: 2.025E-05 | global batch size: 256 | lm loss: 2.908644E+00 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 812.330 | TFLOPs: 5.17 | +31: iteration 37020/ 37905 | consumed samples: 9477120 | consumed tokens: 19409141760 | elapsed time per iteration (s): 0.25 | learning rate: 2.024E-05 | global batch size: 256 | lm loss: 2.861787E+00 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.631 | TFLOPs: 6.49 | +31: 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: 2.901721E+00 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1098.796 | TFLOPs: 7.00 | +31: iteration 37040/ 37905 | consumed samples: 9482240 | consumed tokens: 19419627520 | elapsed time per iteration (s): 0.24 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.881049E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1064.154 | TFLOPs: 6.78 | +31: iteration 37050/ 37905 | consumed samples: 9484800 | consumed tokens: 19424870400 | elapsed time per iteration (s): 0.25 | learning rate: 2.023E-05 | global batch size: 256 | lm loss: 2.905183E+00 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.975 | TFLOPs: 6.59 | +31: iteration 37060/ 37905 | consumed samples: 9487360 | consumed tokens: 19430113280 | elapsed time per iteration (s): 0.26 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 2.882003E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1000.768 | TFLOPs: 6.37 | +31: iteration 37070/ 37905 | consumed samples: 9489920 | consumed tokens: 19435356160 | elapsed time per iteration (s): 0.24 | learning rate: 2.022E-05 | global batch size: 256 | lm loss: 2.877896E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.754 | TFLOPs: 6.79 | +31: iteration 37080/ 37905 | consumed samples: 9492480 | consumed tokens: 19440599040 | elapsed time per iteration (s): 0.27 | learning rate: 2.021E-05 | global batch size: 256 | lm loss: 2.879283E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 950.016 | TFLOPs: 6.05 | +31: 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: 2.907372E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1120.462 | TFLOPs: 7.14 | +31: iteration 37100/ 37905 | consumed samples: 9497600 | consumed tokens: 19451084800 | elapsed time per iteration (s): 0.20 | learning rate: 2.020E-05 | global batch size: 256 | lm loss: 2.876361E+00 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1266.688 | TFLOPs: 8.07 | +31: 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: 2.911300E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1118.006 | TFLOPs: 7.12 | +31: iteration 37120/ 37905 | consumed samples: 9502720 | consumed tokens: 19461570560 | elapsed time per iteration (s): 0.21 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.858933E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1196.532 | TFLOPs: 7.62 | +31: iteration 37130/ 37905 | consumed samples: 9505280 | consumed tokens: 19466813440 | elapsed time per iteration (s): 0.26 | learning rate: 2.019E-05 | global batch size: 256 | lm loss: 2.936755E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 995.961 | TFLOPs: 6.34 | +31: iteration 37140/ 37905 | consumed samples: 9507840 | consumed tokens: 19472056320 | elapsed time per iteration (s): 0.26 | learning rate: 2.018E-05 | global batch size: 256 | lm loss: 2.879073E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 979.663 | TFLOPs: 6.24 | +31: 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: 2.890731E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.519 | TFLOPs: 7.09 | +31: iteration 37160/ 37905 | consumed samples: 9512960 | consumed tokens: 19482542080 | elapsed time per iteration (s): 0.22 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.907544E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1161.499 | TFLOPs: 7.40 | +31: iteration 37170/ 37905 | consumed samples: 9515520 | consumed tokens: 19487784960 | elapsed time per iteration (s): 0.22 | learning rate: 2.017E-05 | global batch size: 256 | lm loss: 2.862463E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1159.759 | TFLOPs: 7.39 | +31: iteration 37180/ 37905 | consumed samples: 9518080 | consumed tokens: 19493027840 | elapsed time per iteration (s): 0.25 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 2.889137E+00 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1020.889 | TFLOPs: 6.50 | +31: iteration 37190/ 37905 | consumed samples: 9520640 | consumed tokens: 19498270720 | elapsed time per iteration (s): 0.27 | learning rate: 2.016E-05 | global batch size: 256 | lm loss: 2.883177E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 948.178 | TFLOPs: 6.04 | +31: iteration 37200/ 37905 | consumed samples: 9523200 | consumed tokens: 19503513600 | elapsed time per iteration (s): 0.22 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.868573E+00 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1169.778 | TFLOPs: 7.45 | +31: iteration 37210/ 37905 | consumed samples: 9525760 | consumed tokens: 19508756480 | elapsed time per iteration (s): 0.25 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.884327E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.714 | TFLOPs: 6.51 | +31: iteration 37220/ 37905 | consumed samples: 9528320 | consumed tokens: 19513999360 | elapsed time per iteration (s): 0.27 | learning rate: 2.015E-05 | global batch size: 256 | lm loss: 2.905689E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 961.549 | TFLOPs: 6.12 | +31: iteration 37230/ 37905 | consumed samples: 9530880 | consumed tokens: 19519242240 | elapsed time per iteration (s): 0.25 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.909416E+00 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1037.292 | TFLOPs: 6.61 | +31: iteration 37240/ 37905 | consumed samples: 9533440 | consumed tokens: 19524485120 | elapsed time per iteration (s): 0.24 | learning rate: 2.014E-05 | global batch size: 256 | lm loss: 2.858282E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1073.459 | TFLOPs: 6.84 | +31: iteration 37250/ 37905 | consumed samples: 9536000 | consumed tokens: 19529728000 | elapsed time per iteration (s): 0.26 | learning rate: 2.013E-05 | global batch size: 256 | lm loss: 2.894456E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 990.320 | TFLOPs: 6.31 | +31: 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: 2.870854E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.655 | TFLOPs: 6.94 | +31: iteration 37270/ 37905 | consumed samples: 9541120 | consumed tokens: 19540213760 | elapsed time per iteration (s): 0.26 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.919415E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 995.596 | TFLOPs: 6.34 | +31: iteration 37280/ 37905 | consumed samples: 9543680 | consumed tokens: 19545456640 | elapsed time per iteration (s): 0.24 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.899510E+00 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1060.928 | TFLOPs: 6.76 | +31: iteration 37290/ 37905 | consumed samples: 9546240 | consumed tokens: 19550699520 | elapsed time per iteration (s): 0.27 | learning rate: 2.012E-05 | global batch size: 256 | lm loss: 2.893467E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 945.100 | TFLOPs: 6.02 | +31: iteration 37300/ 37905 | consumed samples: 9548800 | consumed tokens: 19555942400 | elapsed time per iteration (s): 0.27 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.885123E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 962.175 | TFLOPs: 6.13 | +31: iteration 37310/ 37905 | consumed samples: 9551360 | consumed tokens: 19561185280 | elapsed time per iteration (s): 0.25 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.891409E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.495 | TFLOPs: 6.56 | +31: iteration 37320/ 37905 | consumed samples: 9553920 | consumed tokens: 19566428160 | elapsed time per iteration (s): 0.25 | learning rate: 2.011E-05 | global batch size: 256 | lm loss: 2.887790E+00 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.657 | TFLOPs: 6.51 | +31: iteration 37330/ 37905 | consumed samples: 9556480 | consumed tokens: 19571671040 | elapsed time per iteration (s): 0.25 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.884281E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1010.417 | TFLOPs: 6.44 | +31: iteration 37340/ 37905 | consumed samples: 9559040 | consumed tokens: 19576913920 | elapsed time per iteration (s): 0.25 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.872714E+00 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1028.063 | TFLOPs: 6.55 | +31: iteration 37350/ 37905 | consumed samples: 9561600 | consumed tokens: 19582156800 | elapsed time per iteration (s): 0.24 | learning rate: 2.010E-05 | global batch size: 256 | lm loss: 2.887691E+00 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1075.468 | TFLOPs: 6.85 | +31: iteration 37360/ 37905 | consumed samples: 9564160 | consumed tokens: 19587399680 | elapsed time per iteration (s): 0.27 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.894159E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 960.245 | TFLOPs: 6.12 | +31: iteration 37370/ 37905 | consumed samples: 9566720 | consumed tokens: 19592642560 | elapsed time per iteration (s): 0.24 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.870950E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1074.295 | TFLOPs: 6.84 | +31: iteration 37380/ 37905 | consumed samples: 9569280 | consumed tokens: 19597885440 | elapsed time per iteration (s): 0.26 | learning rate: 2.009E-05 | global batch size: 256 | lm loss: 2.925849E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.666 | TFLOPs: 6.32 | +31: 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: 2.874467E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1110.369 | TFLOPs: 7.07 | +31: 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: 2.875175E+00 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1094.027 | TFLOPs: 6.97 | +31: iteration 37410/ 37905 | consumed samples: 9576960 | consumed tokens: 19613614080 | elapsed time per iteration (s): 0.26 | learning rate: 2.008E-05 | global batch size: 256 | lm loss: 2.842850E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 996.729 | TFLOPs: 6.35 | +31: iteration 37420/ 37905 | consumed samples: 9579520 | consumed tokens: 19618856960 | elapsed time per iteration (s): 0.27 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.864546E+00 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 961.306 | TFLOPs: 6.12 | +31: iteration 37430/ 37905 | consumed samples: 9582080 | consumed tokens: 19624099840 | elapsed time per iteration (s): 0.27 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.881429E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 960.545 | TFLOPs: 6.12 | +31: iteration 37440/ 37905 | consumed samples: 9584640 | consumed tokens: 19629342720 | elapsed time per iteration (s): 0.25 | learning rate: 2.007E-05 | global batch size: 256 | lm loss: 2.867531E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1021.570 | TFLOPs: 6.51 | +31: iteration 37450/ 37905 | consumed samples: 9587200 | consumed tokens: 19634585600 | elapsed time per iteration (s): 0.24 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.899371E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.492 | TFLOPs: 6.81 | +31: iteration 37460/ 37905 | consumed samples: 9589760 | consumed tokens: 19639828480 | elapsed time per iteration (s): 0.21 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.900565E+00 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1231.631 | TFLOPs: 7.84 | +31: iteration 37470/ 37905 | consumed samples: 9592320 | consumed tokens: 19645071360 | elapsed time per iteration (s): 0.24 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.910359E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1065.133 | TFLOPs: 6.78 | +31: iteration 37480/ 37905 | consumed samples: 9594880 | consumed tokens: 19650314240 | elapsed time per iteration (s): 0.24 | learning rate: 2.006E-05 | global batch size: 256 | lm loss: 2.884232E+00 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1086.515 | TFLOPs: 6.92 | +31: iteration 37490/ 37905 | consumed samples: 9597440 | consumed tokens: 19655557120 | elapsed time per iteration (s): 0.24 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.896680E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1048.586 | TFLOPs: 6.68 | +31: iteration 37500/ 37905 | consumed samples: 9600000 | consumed tokens: 19660800000 | elapsed time per iteration (s): 0.25 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.906549E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1024.666 | TFLOPs: 6.53 | +31: iteration 37510/ 37905 | consumed samples: 9602560 | consumed tokens: 19666042880 | elapsed time per iteration (s): 0.28 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.897319E+00 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 928.297 | TFLOPs: 5.91 | +31: iteration 37520/ 37905 | consumed samples: 9605120 | consumed tokens: 19671285760 | elapsed time per iteration (s): 0.25 | learning rate: 2.005E-05 | global batch size: 256 | lm loss: 2.854589E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.339 | TFLOPs: 6.49 | +31: iteration 37530/ 37905 | consumed samples: 9607680 | consumed tokens: 19676528640 | elapsed time per iteration (s): 0.24 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.887199E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1079.021 | TFLOPs: 6.87 | +31: iteration 37540/ 37905 | consumed samples: 9610240 | consumed tokens: 19681771520 | elapsed time per iteration (s): 0.22 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.810824E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1158.875 | TFLOPs: 7.38 | +31: iteration 37550/ 37905 | consumed samples: 9612800 | consumed tokens: 19687014400 | elapsed time per iteration (s): 0.25 | learning rate: 2.004E-05 | global batch size: 256 | lm loss: 2.869536E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1010.034 | TFLOPs: 6.43 | +31: 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: 2.840566E+00 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1059.379 | TFLOPs: 6.75 | +31: iteration 37570/ 37905 | consumed samples: 9617920 | consumed tokens: 19697500160 | elapsed time per iteration (s): 0.25 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.887637E+00 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1018.624 | TFLOPs: 6.49 | +31: iteration 37580/ 37905 | consumed samples: 9620480 | consumed tokens: 19702743040 | elapsed time per iteration (s): 0.24 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.924227E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1058.951 | TFLOPs: 6.74 | +31: 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: 2.864487E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.640 | TFLOPs: 7.14 | +31: 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: 2.909999E+00 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1123.757 | TFLOPs: 7.16 | +31: iteration 37610/ 37905 | consumed samples: 9628160 | consumed tokens: 19718471680 | elapsed time per iteration (s): 0.27 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.895321E+00 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 954.399 | TFLOPs: 6.08 | +31: iteration 37620/ 37905 | consumed samples: 9630720 | consumed tokens: 19723714560 | elapsed time per iteration (s): 0.24 | learning rate: 2.003E-05 | global batch size: 256 | lm loss: 2.915758E+00 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1055.012 | TFLOPs: 6.72 | +31: 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: 2.868991E+00 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1122.157 | TFLOPs: 7.15 | +31: iteration 37640/ 37905 | consumed samples: 9635840 | consumed tokens: 19734200320 | elapsed time per iteration (s): 0.24 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.876520E+00 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1068.526 | TFLOPs: 6.81 | +31: 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: 2.884371E+00 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.396 | TFLOPs: 7.14 | +31: 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: 2.869857E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1089.894 | TFLOPs: 6.94 | +31: 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: 2.855338E+00 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1132.925 | TFLOPs: 7.22 | +31: iteration 37680/ 37905 | consumed samples: 9646080 | consumed tokens: 19755171840 | elapsed time per iteration (s): 0.26 | learning rate: 2.002E-05 | global batch size: 256 | lm loss: 2.880435E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 993.472 | TFLOPs: 6.33 | +31: 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: 2.846978E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1117.426 | TFLOPs: 7.12 | +31: iteration 37700/ 37905 | consumed samples: 9651200 | consumed tokens: 19765657600 | elapsed time per iteration (s): 0.25 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.925961E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1025.670 | TFLOPs: 6.53 | +31: iteration 37710/ 37905 | consumed samples: 9653760 | consumed tokens: 19770900480 | elapsed time per iteration (s): 0.27 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.931453E+00 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 960.190 | TFLOPs: 6.12 | +31: iteration 37720/ 37905 | consumed samples: 9656320 | consumed tokens: 19776143360 | elapsed time per iteration (s): 0.24 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.917255E+00 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1084.486 | TFLOPs: 6.91 | +31: iteration 37730/ 37905 | consumed samples: 9658880 | consumed tokens: 19781386240 | elapsed time per iteration (s): 0.25 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.889783E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1029.260 | TFLOPs: 6.56 | +31: 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: 2.895304E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.248 | TFLOPs: 7.14 | +31: iteration 37750/ 37905 | consumed samples: 9664000 | consumed tokens: 19791872000 | elapsed time per iteration (s): 0.26 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.886700E+00 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 986.213 | TFLOPs: 6.28 | +31: iteration 37760/ 37905 | consumed samples: 9666560 | consumed tokens: 19797114880 | elapsed time per iteration (s): 0.26 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.879058E+00 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 991.591 | TFLOPs: 6.32 | +31: iteration 37770/ 37905 | consumed samples: 9669120 | consumed tokens: 19802357760 | elapsed time per iteration (s): 0.26 | learning rate: 2.001E-05 | global batch size: 256 | lm loss: 2.881442E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 982.331 | TFLOPs: 6.26 | +31: iteration 37780/ 37905 | consumed samples: 9671680 | consumed tokens: 19807600640 | elapsed time per iteration (s): 0.22 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.891814E+00 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1139.352 | TFLOPs: 7.26 | +31: 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: 2.873662E+00 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1095.187 | TFLOPs: 6.98 | +31: iteration 37800/ 37905 | consumed samples: 9676800 | consumed tokens: 19818086400 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.856424E+00 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1033.149 | TFLOPs: 6.58 | +31: 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: 2.843416E+00 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1096.965 | TFLOPs: 6.99 | +31: iteration 37820/ 37905 | consumed samples: 9681920 | consumed tokens: 19828572160 | elapsed time per iteration (s): 0.27 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.873091E+00 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 944.774 | TFLOPs: 6.02 | +31: iteration 37830/ 37905 | consumed samples: 9684480 | consumed tokens: 19833815040 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.917586E+00 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1008.794 | TFLOPs: 6.42 | +31: iteration 37840/ 37905 | consumed samples: 9687040 | consumed tokens: 19839057920 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.860797E+00 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1012.706 | TFLOPs: 6.45 | +31: iteration 37850/ 37905 | consumed samples: 9689600 | consumed tokens: 19844300800 | elapsed time per iteration (s): 0.26 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.887733E+00 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 992.282 | TFLOPs: 6.32 | +31: 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: 2.911167E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1121.920 | TFLOPs: 7.15 | +31: iteration 37870/ 37905 | consumed samples: 9694720 | consumed tokens: 19854786560 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.897402E+00 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1050.629 | TFLOPs: 6.69 | +31: iteration 37880/ 37905 | consumed samples: 9697280 | consumed tokens: 19860029440 | elapsed time per iteration (s): 0.25 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.891303E+00 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1034.542 | TFLOPs: 6.59 | +31: iteration 37890/ 37905 | consumed samples: 9699840 | consumed tokens: 19865272320 | elapsed time per iteration (s): 0.24 | learning rate: 2.000E-05 | global batch size: 256 | lm loss: 2.901179E+00 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1067.682 | TFLOPs: 6.80 | +31: 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: 2.862957E+00 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 1112.287 | TFLOPs: 7.08 | + 0: [after training is done] datetime: 2022-11-24 17:13:45 + 0: saving checkpoint at iteration 37905 to checkpoints_83m +31: ------------------------------------------------------------------------------------------------------------ +31: valid loss at the end of training for val data | lm loss value: 2.851934E+00 | lm loss PPL: 1.732125E+01 | +31: ------------------------------------------------------------------------------------------------------------ + 0: [2022-11-24 17:13:45,254] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step37905 is begin to save! + 0: [2022-11-24 17:13:45,265] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_01-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_01-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,338] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_03-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_03-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_04-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_04-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,362] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_05-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_05-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,373] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_06-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_06-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,384] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_07-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_07-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,395] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_08-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_08-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,407] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_09-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_09-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,418] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_10-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,429] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_10-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,429] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_11-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_11-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,440] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_12-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_12-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/layer_14-model_00-model_states.pt... + 0: [2022-11-24 17:13:45,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/layer_14-model_00-model_states.pt. + 0: [2022-11-24 17:13:45,452] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: checkpoints_83m/global_step37905/mp_rank_00_model_states.pt + 0: [2022-11-24 17:13:45,452] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/mp_rank_00_model_states.pt... + 0: [2022-11-24 17:13:45,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/mp_rank_00_model_states.pt. + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt... +24: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt... + 7: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt... +12: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt... +23: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt... +31: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt... +22: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt... +16: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt... +29: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt... +11: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt... +26: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt... + 3: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt... +14: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt... +15: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt... +27: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt... +20: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt... +10: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt... + 4: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt... +18: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt... +25: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt... +30: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt... +21: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt... +13: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... + 5: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt... + 6: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt... + 1: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +19: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt... + 8: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt... + 9: [2022-11-24 17:13:45,521] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt... + 0: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +17: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt... +28: [2022-11-24 17:13:45,520] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving checkpoints_83m/global_step37905/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt... + 2: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:13:45,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_121_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 9: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_78_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,527] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_85_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_139_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +29: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_238_mp_rank_00_optim_states.pt +29: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:13:45,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_60_mp_rank_00_optim_states.pt +11: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,528] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_95_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,528] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +20: [2022-11-24 17:13:45,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_163_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 8: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_65_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:13:45,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +16: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,529] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_128_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_225_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +25: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_200_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_177_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_153_mp_rank_00_optim_states.pt +22: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +19: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:13:45,530] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_208_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_197_mp_rank_00_optim_states.pt +24: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +12: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 2: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:13:45,531] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_123_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_72_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_217_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_89_mp_rank_00_optim_states.pt +11: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,532] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_136_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,532] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:13:45,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_165_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_151_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_186_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_237_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_83_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,533] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_57_mp_rank_00_optim_states.pt +29: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:13:45,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_117_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:13:45,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_175_mp_rank_00_optim_states.pt +21: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +16: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_131_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,534] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,534] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_209_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 8: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_71_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_229_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +25: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_205_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 6: [2022-11-24 17:13:45,535] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_54_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,535] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +19: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_159_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:13:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +22: [2022-11-24 17:13:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_179_mp_rank_00_optim_states.pt +22: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_246_mp_rank_00_optim_states.pt +30: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +31: [2022-11-24 17:13:45,536] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_254_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,536] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_96_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 2: [2022-11-24 17:13:45,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:13:45,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_218_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_73_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,537] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_124_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:13:45,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_192_mp_rank_00_optim_states.pt +24: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_94_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,538] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_137_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,538] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +20: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_166_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +29: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_235_mp_rank_00_optim_states.pt +29: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:13:45,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_62_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,539] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_84_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_118_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,539] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +16: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_129_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:13:45,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_150_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,540] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_212_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:13:45,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_173_mp_rank_00_optim_states.pt +21: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_189_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_67_mp_rank_00_optim_states.pt +23: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 8: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_228_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 6: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,541] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_55_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,541] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +25: [2022-11-24 17:13:45,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_206_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +19: [2022-11-24 17:13:45,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_152_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:13:45,542] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +22: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_181_mp_rank_00_optim_states.pt +22: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_240_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +31: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_255_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 2: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_99_mp_rank_00_optim_states.pt +12: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:13:45,543] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:13:45,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_125_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:13:45,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_194_mp_rank_00_optim_states.pt +24: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 9: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_77_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:13:45,544] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_222_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_143_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_88_mp_rank_00_optim_states.pt +11: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +20: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_161_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_239_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_59_mp_rank_00_optim_states.pt +29: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,545] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_81_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:13:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_119_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_134_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_146_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:13:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_213_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,546] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:13:45,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_169_mp_rank_00_optim_states.pt +21: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 8: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_69_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_187_mp_rank_00_optim_states.pt +23: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_226_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +25: [2022-11-24 17:13:45,547] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,547] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_202_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 6: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +19: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_156_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_244_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_250_mp_rank_00_optim_states.pt +30: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +31: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,548] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,548] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +22: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_180_mp_rank_00_optim_states.pt +22: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_98_mp_rank_00_optim_states.pt +12: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 2: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,549] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:13:45,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:13:45,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_127_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 9: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_75_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:13:45,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_196_mp_rank_00_optim_states.pt +24: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:13:45,550] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_216_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,550] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_91_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_138_mp_rank_00_optim_states.pt +11: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:13:45,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +20: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,551] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_160_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +29: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_233_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_58_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:13:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_149_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_114_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,552] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_87_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:13:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_210_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_130_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +16: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 8: [2022-11-24 17:13:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_68_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:13:45,553] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_168_mp_rank_00_optim_states.pt +21: [2022-11-24 17:13:45,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_190_mp_rank_00_optim_states.pt +23: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_224_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 6: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +25: [2022-11-24 17:13:45,554] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_203_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +19: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_155_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:13:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_245_mp_rank_00_optim_states.pt +30: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:13:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +31: [2022-11-24 17:13:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_251_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,555] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_249_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +31: [2022-11-24 17:13:45,555] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +22: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_182_mp_rank_00_optim_states.pt +22: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +12: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 2: [2022-11-24 17:13:45,556] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:13:45,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_126_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:13:45,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_195_mp_rank_00_optim_states.pt +24: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 9: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_74_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:13:45,557] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_220_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_92_mp_rank_00_optim_states.pt +11: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_142_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +20: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,558] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_162_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +29: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_234_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_63_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_80_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:13:45,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:13:45,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_144_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +16: [2022-11-24 17:13:45,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,559] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_132_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:13:45,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_211_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 8: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_66_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_184_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +21: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:13:45,560] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_174_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 6: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +25: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_207_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_230_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +19: [2022-11-24 17:13:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_157_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_241_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,561] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +22: [2022-11-24 17:13:45,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,562] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_176_mp_rank_00_optim_states.pt +22: [2022-11-24 17:13:45,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:13:45,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_97_mp_rank_00_optim_states.pt +12: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 2: [2022-11-24 17:13:45,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt. +15: [2022-11-24 17:13:45,563] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_120_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,563] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:13:45,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_223_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:13:45,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_199_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 9: [2022-11-24 17:13:45,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_76_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_90_mp_rank_00_optim_states.pt +11: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt. +17: [2022-11-24 17:13:45,564] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_141_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:13:45,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +20: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_164_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 7: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:13:45,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_61_mp_rank_00_optim_states.pt +29: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +29: [2022-11-24 17:13:45,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_232_mp_rank_00_optim_states.pt +29: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,565] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_86_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:13:45,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_145_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:13:45,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_115_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +16: [2022-11-24 17:13:45,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_133_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:13:45,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_214_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,566] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 8: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_64_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:13:45,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_171_mp_rank_00_optim_states.pt +21: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_185_mp_rank_00_optim_states.pt +23: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_231_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +25: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,567] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_201_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,567] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 6: [2022-11-24 17:13:45,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +19: [2022-11-24 17:13:45,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_158_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,568] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_243_mp_rank_00_optim_states.pt +30: [2022-11-24 17:13:45,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +12: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt. +14: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_188_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt. +19: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_154_mp_rank_00_optim_states.pt + 2: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt. +16: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt. +13: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt. +12: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt. +29: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt. +11: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt. +23: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +31: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_252_mp_rank_00_optim_states.pt +14: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_116_mp_rank_00_optim_states.pt +19: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 2: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt. +25: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_204_mp_rank_00_optim_states.pt + 9: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_79_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt. +28: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt. + 0: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. + 7: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_56_mp_rank_00_optim_states.pt +12: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +29: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_236_mp_rank_00_optim_states.pt +11: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_93_mp_rank_00_optim_states.pt +23: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +14: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 1: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. + 2: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_183_mp_rank_00_optim_states.pt +10: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt. + 4: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt. + 8: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_70_mp_rank_00_optim_states.pt +16: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_135_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_147_mp_rank_00_optim_states.pt +25: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt. + 9: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +13: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt + 0: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt + 7: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +12: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +29: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +11: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_191_mp_rank_00_optim_states.pt +26: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt. + 1: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +15: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_122_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_219_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt. +22: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +10: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_82_mp_rank_00_optim_states.pt + 4: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt + 8: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +16: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_247_mp_rank_00_optim_states.pt +17: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_140_mp_rank_00_optim_states.pt +28: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_227_mp_rank_00_optim_states.pt +13: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +23: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +26: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_215_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_253_mp_rank_00_optim_states.pt + 1: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +15: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt. +10: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 4: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +18: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt. +30: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +17: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +28: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt. +21: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt. +26: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt. + 3: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt. +31: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +27: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt. +20: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_167_mp_rank_00_optim_states.pt +22: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt. +24: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt. +18: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_148_mp_rank_00_optim_states.pt +30: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt. + 6: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_53_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt. +27: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_221_mp_rank_00_optim_states.pt +20: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +22: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_178_mp_rank_00_optim_states.pt +24: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_193_mp_rank_00_optim_states.pt +18: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +30: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_242_mp_rank_00_optim_states.pt +21: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_170_mp_rank_00_optim_states.pt + 6: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 6: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +31: [2022-11-24 17:13:45,569] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_248_mp_rank_00_optim_states.pt +27: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +22: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_198_mp_rank_00_optim_states.pt +30: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,570] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_172_mp_rank_00_optim_states.pt + 3: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +31: [2022-11-24 17:13:45,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 3: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +24: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! +21: [2022-11-24 17:13:45,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 5: [2022-11-24 17:13:45,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt. + 5: [2022-11-24 17:13:45,571] [INFO] [engine.py:3213:_save_zero_checkpoint] bf16_zero checkpoint saved checkpoints_83m/global_step37905/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt + 5: [2022-11-24 17:13:45,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step37905 is ready now! + 0: successfully saved checkpoint at iteration 37905 to checkpoints_83m +31: ------------------------------------------------------------------------------------------------------------ +31: test loss at the end of training for test data | lm loss value: 2.767530E+00 | lm loss PPL: 1.591926E+01 | +31: ------------------------------------------------------------------------------------------------------------ +28: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 4: END 2058110: Thu Nov 24 17:13:52 EET 2022 +20: END 2058110: Thu Nov 24 17:13:52 EET 2022 +17: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 7: END 2058110: Thu Nov 24 17:13:52 EET 2022 +16: END 2058110: Thu Nov 24 17:13:52 EET 2022 +12: END 2058110: Thu Nov 24 17:13:52 EET 2022 +19: END 2058110: Thu Nov 24 17:13:52 EET 2022 +25: END 2058110: Thu Nov 24 17:13:52 EET 2022 +26: END 2058110: Thu Nov 24 17:13:52 EET 2022 +15: END 2058110: Thu Nov 24 17:13:52 EET 2022 +14: END 2058110: Thu Nov 24 17:13:52 EET 2022 +27: END 2058110: Thu Nov 24 17:13:52 EET 2022 +24: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 5: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 9: END 2058110: Thu Nov 24 17:13:52 EET 2022 +18: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 6: END 2058110: Thu Nov 24 17:13:52 EET 2022 +11: END 2058110: Thu Nov 24 17:13:52 EET 2022 +22: END 2058110: Thu Nov 24 17:13:52 EET 2022 +29: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 0: END 2058110: Thu Nov 24 17:13:52 EET 2022 +31: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 1: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 2: END 2058110: Thu Nov 24 17:13:52 EET 2022 +23: END 2058110: Thu Nov 24 17:13:52 EET 2022 +10: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 8: END 2058110: Thu Nov 24 17:13:52 EET 2022 + 3: END 2058110: Thu Nov 24 17:13:52 EET 2022 +13: END 2058110: Thu Nov 24 17:13:52 EET 2022 +30: END 2058110: Thu Nov 24 17:13:52 EET 2022 +21: END 2058110: Thu Nov 24 17:13:52 EET 2022 diff --git a/tensorboard/events.out.tfevents.1669291936.nid005423.114100.0 b/tensorboard/events.out.tfevents.1669291936.nid005423.114100.0 new file mode 100644 index 0000000000000000000000000000000000000000..f21025f6ef0e9eb6691ae9962e58eab0d8c710b1 --- /dev/null +++ b/tensorboard/events.out.tfevents.1669291936.nid005423.114100.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f844f7842970c29eb4ded4d88ed1bb2cf77a3af322b28096cd8fcb2cb4a1a9 +size 64855142 diff --git a/tensorboard/events.out.tfevents.1669301259.nid005423.40010.0 b/tensorboard/events.out.tfevents.1669301259.nid005423.40010.0 new file mode 100644 index 0000000000000000000000000000000000000000..28e0e42e2af515b970fa72ce8f452b9899ce333d --- /dev/null +++ b/tensorboard/events.out.tfevents.1669301259.nid005423.40010.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fff8277bf8482f0738b7903f0e443f04cab8b7936f3916a5d1e4ed6f4ab3808 +size 1810227 diff --git a/tensorboard/events.out.tfevents.1669302300.nid005423.48734.0 b/tensorboard/events.out.tfevents.1669302300.nid005423.48734.0 new file mode 100644 index 0000000000000000000000000000000000000000..03068b887d8c09e6c2637f344920916b0765e1ed --- /dev/null +++ b/tensorboard/events.out.tfevents.1669302300.nid005423.48734.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61984254b13ca18ad66226bbdc941e1716808d6971f533881239e2e10df35a22 +size 3432602